© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 5760
    Prev
    Next
    INDEX
    Explanations

    code related to creating and setting up user interface components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.82
    astify
    -0.72
    })*/
    -0.66
    "]];
    -0.65
    }\]
    -0.65
    bigoplus
    -0.64
    __(/*!
    -0.64
    propTypes
    -0.61
    GraphicsUnit
    -0.60
    abbaye
    -0.59
    POSITIVE LOGITS
     onCreateView
    0.96
     unknownFields
    0.89
     cref
    0.86
     مشين
    0.73
    styleUrls
    0.72
    )(((
    0.71
    msgSender
    0.66
     препратки
    0.65
    setContentView
    0.64
    UTC
    0.61
    Activations Density 0.007%

    No Known Activations