© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12080
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific measurements and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical or scientific relationships that are "inversely proportional" or follow an inverse scaling pattern.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    inverse proportional relationships and scaling laws.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.60
     ब्रेकडाउन
    -0.58
     EconPapers
    -0.57
     NSCoder
    -0.52
     resourceCulture
    -0.52
    RectangleBorder
    -0.51
     estekak
    -0.49
    sidemargin
    -0.49
    enderror
    -0.48
    RuleContext
    -0.47
    POSITIVE LOGITS
     linear
    1.52
     proportional
    1.48
     proportionality
    1.36
    linear
    1.30
     linearly
    1.29
     Linear
    1.20
    propor
    1.19
     proportionate
    1.19
     proportionally
    1.16
     liné
    1.15
    Activations Density 1.764%

    No Known Activations