© 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. 4-GEMMASCOPE-RES-16K
    6. 10727
    Prev
    Next
    INDEX
    Explanations

    commands and flags used in system operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]);
    
    -0.57
    "]];
    -0.56
    »),
    -0.54
    )))),
    -0.54
    _),
    -0.54
    ))),
    -0.52
    ftagPool
    -0.51
    __))
    -0.51
    ])),
    -0.50
    doGet
    -0.50
    POSITIVE LOGITS
    ússia
    0.77
    enterOuterAlt
    0.72
    tiary
    0.69
    ButtonModule
    0.67
    Pyx
    0.67
     ajudá
    0.65
    migrationBuilder
    0.65
    ALLENGE
    0.65
    protoimpl
    0.64
     chi̍t
    0.64
    Activations Density 0.208%

    No Known Activations