© 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. 13500
    Prev
    Next
    INDEX
    Explanations

    conjunctions and related expressions connecting alternatives and agreements in argumentative or evaluative contexts

    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
    glEnable
    -0.54
    }_{+
    -0.52
    _{+}
    -0.51
    jsonwebtoken
    -0.50
    fycat
    -0.49
    ^{+}$
    -0.48
    IsTrue
    -0.48
    }^{+}$
    -0.47
    ++]
    -0.47
    ThroughAttribute
    -0.46
    POSITIVE LOGITS
     negative
    1.05
     negatives
    0.98
    negative
    0.94
     downside
    0.91
    Negative
    0.87
     disadvantages
    0.86
     Minus
    0.85
     negativo
    0.83
     Negative
    0.83
     negativos
    0.82
    Activations Density 1.125%

    No Known Activations