© 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. 4-GEMMASCOPE-RES-16K
    11. 16251
    Prev
    Next
    INDEX
    Explanations

    phrases and words referring to actions and their sufficiency or necessity

    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
    ⓧ
    -0.62
    はじめに
    -0.61
    artifactId
    -0.60
    rungsseite
    -0.58
    IVEREF
    -0.57
    }}"
    -0.56
    raszam
    -0.56
    asticity
    -0.56
     cherchés
    -0.56
    ]")]
    -0.56
    POSITIVE LOGITS
     sufficient
    1.08
     Sufficient
    1.02
     suffices
    1.01
     Enough
    1.00
     enough
    1.00
     suffic
    0.99
    sufficient
    0.93
     genü
    0.89
     suffit
    0.88
     کافی
    0.88
    Activations Density 0.137%

    No Known Activations