© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1386
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and formal definitions involving probability and statistics

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

    mathematical and statistical notation and terminology in formal proofs.

    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
    mot
    -0.38
    InitStruct
    -0.37
     dro
    -0.36
     kira
    -0.36
    twimg
    -0.35
     trùng
    -0.35
    EndContext
    -0.35
    icana
    -0.34
    esModule
    -0.34
    descr
    -0.33
    POSITIVE LOGITS
    LabelTagHelper
    0.57
    BagConstraints
    0.54
    NameInMap
    0.52
     sufficiently
    0.50
     doInBackground
    0.49
    OGND
    0.49
    IVEREF
    0.49
     CreateTagHelper
    0.49
    ɵɵelementStart
    0.49
    InjectAttribute
    0.46
    Activations Density 1.744%

    No Known Activations