Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10178
    Prev
    Next
    INDEX
    Explanations

    instances of italicized text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceaux
    -0.58
    arakhand
    -0.58
    <eos>
    -0.58
     weeks
    -0.56
    rinfo
    -0.55
    Autoritní
    -0.55
    Географиясе
    -0.52
     days
    -0.52
     Drummond
    -0.52
     towels
    -0.51
    POSITIVE LOGITS
    </em>
    1.75
    </i>
    1.33
    </h6>
    1.13
    };*/
    1.03
    }*/
    
    1.00
    });*/
    0.97
    rrggbb
    0.93
    */;
    0.89
    );*/
    0.88
     Saltar
    0.87
    Activations Density 0.090%

    No Known Activations