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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 5559
    Prev
    Next
    INDEX
    Explanations

    specific identifiable names or terms related to studies, chemicals, or agents in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     correcto
    -0.47
    ResumeLayout
    -0.45
    ETHING
    -0.40
    ConstraintMaker
    -0.39
     kaikk
    -0.39
    zentrum
    -0.37
     Signalez
    -0.37
     proper
    -0.37
    MarshalTo
    -0.36
     дописавши
    -0.36
    POSITIVE LOGITS
    sz
    0.54
    sar
    0.52
    song
    0.49
    sch
    0.47
    ⿻
    0.47
     pz
    0.46
    sing
    0.45
    sung
    0.44
    singer
    0.44
    sat
    0.44
    Activations Density 0.269%

    No Known Activations