© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 8856
    Prev
    Next
    INDEX
    Explanations

    geographical names, particularly those related to Los Angeles and Fort Meade

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.96
     Shakspeare
    -0.72
    Дереккөздер
    -0.70
    ItemBackground
    -0.69
     Mahomet
    -0.66
     Shaksp
    -0.66
     Theſe
    -0.66
    liferay
    -0.64
    ngdoc
    -0.63
     Phry
    -0.63
    POSITIVE LOGITS
     Meksiku
    0.61
    principalTable
    0.45
     Fe
    0.44
     NSCoder
    0.41
    RestController
    0.41
     fede
    0.41
     Segal
    0.40
    pless
    0.40
    Fe
    0.39
    {(-
    0.39
    Activations Density 0.126%

    No Known Activations