© 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. 9-GEMMASCOPE-RES-16K
    6. 15488
    Prev
    Next
    INDEX
    Explanations

    references to internal communications or internal processes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.74
     casado
    -0.74
     McClure
    -0.72
     fjord
    -0.71
    ]")]
    -0.71
    Gonna
    -0.71
     cappella
    -0.69
     AudioClip
    -0.69
     yeezy
    -0.68
     Koa
    -0.68
    POSITIVE LOGITS
     Internal
    1.26
     internal
    1.25
     INTERNAL
    1.17
    Internal
    1.13
     internally
    1.13
    internal
    1.07
    INTERNAL
    1.03
    InternalFrame
    1.03
     Intern
    0.93
    ternal
    0.91
    Activations Density 0.109%

    No Known Activations