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. 2-GEMMASCOPE-RES-16K
    6. 6173
    Prev
    Next
    INDEX
    Explanations

    instances and references to gene expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"/
    -0.78
    раздо
    -0.78
    pgsql
    -0.74
    鬟
    -0.70
    +#+#
    -0.67
    makedirs
    -0.67
    Bakgrunnsstoff
    -0.66
    ittäin
    -0.66
    britannien
    -0.66
    جغرافيا
    -0.64
    POSITIVE LOGITS
     expression
    3.63
    expression
    3.30
     Expression
    3.29
     expressions
    3.18
    Expression
    3.15
    expressions
    2.82
     Expressions
    2.80
    Expressions
    2.53
     expresión
    2.48
     expressão
    2.38
    Activations Density 0.117%

    No Known Activations