© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 5342
    Prev
    Next
    INDEX
    Explanations

    structural elements and terms related to data or schema definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])),
    -0.88
    `;
    
    -0.83
    })),
    -0.82
    ")}
    -0.81
    ))),
    -0.80
    ";}
    -0.79
    %;">
    -0.79
    "]));
    -0.79
    []);
    -0.78
     }}$}
    -0.77
    POSITIVE LOGITS
    chiato
    0.48
    بوابة
    0.48
    __()
    0.43
    UITableView
    0.42
    PMailer
    0.42
    TagMode
    0.41
    aringan
    0.41
    illoin
    0.41
    jár
    0.40
     Pad
    0.40
    Activations Density 0.402%

    No Known Activations