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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 4686
    Prev
    Next
    INDEX
    Explanations

    closing brackets and semicolons, indicating the end of code blocks or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trin
    -0.80
    Faust
    -0.75
    Cass
    -0.74
    igshid
    -0.70
     FormsModule
    -0.68
    াক
    -0.67
    plom
    -0.67
    bond
    -0.66
    IN
    -0.66
    fileID
    -0.66
    POSITIVE LOGITS
    ,:);
    1.26
    ]]);
    1.23
    })));
    1.19
    {};
    1.13
    +};
    1.13
    ]};
    1.11
    )};
    1.10
    '};
    1.07
    }';
    1.03
    )();
    1.02
    Activations Density 0.156%

    No Known Activations