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. 5810
    Prev
    Next
    INDEX
    Explanations

    contextual details related to financial transactions and agreements

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

    Token before "val" or "Val"

    np_acts-logits-general · gemini-2.0-flash

    variable assignment or value containing 'val'

    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
     Moor
    -0.71
    SourceChecksum
    -0.64
    Moor
    -0.59
    jsonwebtoken
    -0.58
     Leland
    -0.58
     ASR
    -0.57
    AndroidJUnit
    -0.56
     Sarmiento
    -0.56
     Camacho
    -0.55
     eosin
    -0.54
    POSITIVE LOGITS
     Val
    3.12
     val
    3.11
    Val
    3.03
    val
    2.95
     VAL
    2.77
    VAL
    2.72
     Valerie
    1.81
     Vali
    1.75
    vals
    1.72
     vals
    1.69
    Activations Density 0.275%

    No Known Activations