© 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. 7-GEMMASCOPE-RES-16K
    6. 7367
    Prev
    Next
    INDEX
    Explanations

    code structure elements such as function definitions and control flow statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Montal
    -0.79
    audiovisuel
    -0.72
    (\"
    -0.67
    örté
    -0.67
     Khal
    -0.66
     \"%
    -0.66
     Zun
    -0.66
    avyzd
    -0.65
    transQ
    -0.65
    =
    
    -0.64
    POSITIVE LOGITS
    }());
    1.12
    endphp
    1.07
    )))));
    0.86
    ))));
    0.85
    ])))
    0.82
     الحره
    0.82
    ↵↵
    0.81
    })));
    0.81
    </blockquote>
    0.80
    )));
    0.77
    Activations Density 0.072%

    No Known Activations