© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 1973
    Prev
    Next
    INDEX
    Explanations

    programming language constructs and expressions related to recursion and function calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ӕ
    -0.57
    Tikang
    -0.53
     surla
    -0.49
    fromnode
    -0.49
    Попис
    -0.47
    LabelTagHelper
    -0.46
    AddTagHelper
    -0.44
    OwnProperty
    -0.44
    VersionUID
    -0.44
    省市镇
    -0.43
    POSITIVE LOGITS
    tagext
    0.41
     contigo
    0.35
     CONDU
    0.35
     postura
    0.34
     casse
    0.34
     Ketten
    0.33
    thalene
    0.33
     appointments
    0.32
     apunta
    0.32
    Candid
    0.31
    Activations Density 0.301%

    No Known Activations