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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 7402
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to assumptions and models in statistical analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -1.06
     myſelf
    -1.06
     Efq
    -1.05
     ſind
    -1.00
    MigrationBuilder
    -1.00
    ^(@)
    -0.99
     iſt
    -0.99
     doubtnut
    -0.97
     ―――――
    -0.96
     Jefus
    -0.96
    POSITIVE LOGITS
     or
    0.73
    -
    0.58
     (
    0.58
     de
    0.58
     in
    0.57
    </b>
    0.54
    ,
    0.54
     and
    0.53
    /
    0.50
     si
    0.50
    Activations Density 0.221%

    No Known Activations