Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13071
    Prev
    Next
    INDEX
    Explanations

    API request patterns related to specific actions and resource management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Values associated with "extendsDataType"

    np_acts-logits-general · gemini-2.0-flash

    data structure definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orderid
    -0.77
    getdata
    -0.69
    getvalue
    -0.66
    newnode
    -0.64
    startdate
    -0.63
    groupid
    -0.62
    companyname
    -0.57
    userinfo
    -0.56
    enddate
    -0.56
    fieldname
    -0.55
    POSITIVE LOGITS
     propOrder
    0.89
    Personendaten
    0.85
    styleType
    0.81
     iD
    0.81
     CanadaChoose
    0.79
     unknownFields
    0.79
    iQ
    0.77
    tagHelperRunner
    0.76
    WithIOException
    0.76
    IsMutable
    0.74
    Activations Density 0.348%

    No Known Activations