© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14275
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming functions or operations

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

    Code or math containing the letter "v"

    np_acts-logits-general · gemini-2.0-flash

    v in mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.68
    Tikang
    -0.67
     مشين
    -0.56
    Према
    -0.53
    windowFixed
    -0.53
     beginnetje
    -0.50
    AccessorTable
    -0.48
    __":
    -0.48
    __':
    -0.47
     ProtoMessage
    -0.47
    POSITIVE LOGITS
     v
    3.14
    v
    2.63
    ｖ
    1.32
     vv
    1.32
    𝑣
    1.13
    getV
    1.12
    vv
    1.12
    vB
    1.00
     V
    1.00
     vlog
    0.99
    Activations Density 0.523%

    No Known Activations