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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 4823
    Prev
    Next
    INDEX
    Explanations

    phrases indicating transition or movement into a new state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.71
     queſta
    -0.70
    <unused42>
    -0.70
    <unused43>
    -0.69
    <unused74>
    -0.69
    <unused41>
    -0.69
    <unused28>
    -0.69
     ModelExpression
    -0.69
    <unused17>
    -0.69
    <unused8>
    -0.69
    POSITIVE LOGITS
     into
    1.59
     toward
    1.48
     hacia
    1.41
     towards
    1.41
     onto
    1.40
    into
    1.40
     forward
    1.38
     INTO
    1.32
    Into
    1.24
     downwards
    1.22
    Activations Density 0.357%

    No Known Activations