© 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. 25-GEMMASCOPE-RES-16K
    11. 233
    Prev
    Next
    INDEX
    Explanations

    terms related to validity, legality, and classification distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kommunen
    -0.64
    ()].
    -0.59
    ()]);
    -0.56
    ()));
    -0.53
    这件事
    -0.52
    sstelle
    -0.52
    ());
    -0.51
    bouncycastle
    -0.49
    ()];
    -0.49
    "]);
    -0.48
    POSITIVE LOGITS
    principalTable
    0.63
     ones
    0.63
    ///</
    0.59
    הערות
    0.59
    WebVitals
    0.58
     initComponents
    0.57
     CommonModule
    0.56
    Izvori
    0.55
     arşivlendi
    0.55
     Theſe
    0.55
    Activations Density 0.909%

    No Known Activations