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. 7845
    Prev
    Next
    INDEX
    Explanations

    elements related to database connection options and configurations

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

    SQL statements/commands

    np_acts-logits-general · gemini-2.0-flash

    SQL statements and database access

    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
     ddelweddau
    -0.57
     UIImageView
    -0.56
     ур
    -0.53
     denk
    -0.53
    fano
    -0.53
     OIL
    -0.51
    virons
    -0.50
     dif
    -0.50
     Torre
    -0.50
     Oil
    -0.50
    POSITIVE LOGITS
    Statement
    0.76
     Statement
    0.69
    Prepared
    0.65
    prepareStatement
    0.62
     Prepared
    0.62
    statement
    0.60
    Statements
    0.60
    stmt
    0.59
     <<<<<<<<<<<<<<
    0.59
     STATEMENT
    0.58
    Activations Density 0.056%

    No Known Activations