© 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. 38-GEMMASCOPE-RES-16K
    11. 15380
    Prev
    Next
    INDEX
    Explanations

    information related to clinical studies and therapies for genetic diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.58
    #+#
    -0.51
    RTSC
    -0.43
    AnchorStyles
    -0.42
    uVar
    -0.41
     BoxFit
    -0.41
     ThemeData
    -0.40
     StatefulWidget
    -0.39
     Roskov
    -0.38
     AssemblyTitle
    -0.38
    POSITIVE LOGITS
     investig
    0.74
     investigator
    0.63
     Investig
    0.61
     indications
    0.61
     Investigator
    0.58
    Investig
    0.58
    investig
    0.57
    Indication
    0.56
     indication
    0.55
     Efficacy
    0.54
    Activations Density 1.958%

    No Known Activations