© 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. 35-GEMMASCOPE-RES-16K
    11. 7664
    Prev
    Next
    INDEX
    Explanations

    questions and speculative language regarding situations or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vordergrund
    -0.43
    TypedDataSet
    -0.42
    StructEnd
    -0.42
     Signalez
    -0.41
    hibli
    -0.40
    存在的
    -0.40
    writeFieldEnd
    -0.40
    новниш
    -0.39
    DockStyle
    -0.38
     fört
    -0.38
    POSITIVE LOGITS
     happen
    1.59
     happens
    1.46
     happened
    1.42
     HAPP
    1.25
    happen
    1.20
     Happen
    1.19
     happ
    1.14
    happens
    1.10
     happening
    1.09
     Happens
    1.05
    Activations Density 0.274%

    No Known Activations