© 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. 4805
    Prev
    Next
    INDEX
    Explanations

    terms related to process completion and approval

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

    words related to procedural or instructional language, particularly phrases involving checking, reviewing, or verifying information before taking action.

    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
     TextAppearance
    -0.68
    enterOuterAlt
    -0.55
    principalColumn
    -0.54
    MessageOf
    -0.50
    FunctionFlags
    -0.49
     nakalista
    -0.49
    ItemBackground
    -0.48
    UALA
    -0.48
    localctx
    -0.48
    enumii
    -0.47
    POSITIVE LOGITS
     before
    3.75
    before
    3.09
     sebelum
    3.00
     antes
    2.97
     Before
    2.84
    Before
    2.83
     ennen
    2.72
     BEFORE
    2.56
     înainte
    2.52
     قبل
    2.50
    Activations Density 2.239%

    No Known Activations