© 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. 22-GEMMASCOPE-RES-16K
    11. 12676
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical values and their associated symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hexadecimal and numerical codes

    np_acts-logits-general · gemini-2.0-flash

    code structure terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.73
    rungsseite
    -0.70
    ništvo
    -0.70
    таратура
    -0.69
    Portail
    -0.66
    országban
    -0.64
     Monfieur
    -0.63
     TPE
    -0.63
    Erreferentziak
    -0.63
    providedIn
    -0.61
    POSITIVE LOGITS
    bottomrule
    0.68
    </tbody>
    0.67
    ];
    0.64
    ]
    0.61
    ]</
    0.57
    };
    0.55
    }
    0.55
    }}}
    0.55
     CONCLUSION
    0.55
    </
    0.55
    Activations Density 0.635%

    No Known Activations