© 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. 5-GEMMASCOPE-RES-16K
    6. 3354
    Prev
    Next
    INDEX
    Explanations

    mark-up tags or indicators in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.97
    ########.
    -0.89
    MigrationBuilder
    -0.88
    rrggbb
    -0.81
    extAlignment
    -0.73
     turística
    -0.73
    Sucesor
    -0.72
     Bluestacks
    -0.71
    RegistryLite
    -0.71
    QMetaType
    -0.69
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.65
    CppMethod
    0.50
    Ÿ
    0.48
    matic
    0.47
     deten
    0.47
    t
    0.47
    LIOT
    0.46
    hyd
    0.46
     faut
    0.46
    خر
    0.46
    Activations Density 0.047%

    No Known Activations