© 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. 11543
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or groups and their contributions or characteristics

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

    first-person narrative or subjective perspectives using pronouns like "I" and "we" combined with action verbs.

    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
    inSlope
    -0.49
    __":
    -0.45
    ẖ
    -0.39
    までに
    -0.39
    ValueStyle
    -0.36
     perchance
    -0.36
    MessageTagHelper
    -0.36
    RTLR
    -0.36
     endfor
    -0.36
    ParallelGroup
    -0.35
    POSITIVE LOGITS
     always
    4.00
    always
    3.59
    Always
    3.36
     Always
    3.33
     siempre
    3.33
     sempre
    3.27
     zawsze
    3.08
     всегда
    3.00
     selalu
    2.95
     ALWAYS
    2.95
    Activations Density 1.349%

    No Known Activations