© 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. 2-GEMMASCOPE-RES-16K
    6. 3927
    Prev
    Next
    INDEX
    Explanations

    the closing braces and semicolons in a programming or scripting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ա
    -0.58
     dold
    -0.55
    illoma
    -0.55
     जु
    -0.54
     Geor
    -0.54
    chak
    -0.54
    <![
    -0.54
     response
    -0.53
     Heuer
    -0.53
     responses
    -0.52
    POSITIVE LOGITS
    };
    2.10
    };
    
    1.99
     };
    1.77
     };
    
    1.57
    '};
    1.56
    ()};
    1.46
    "};
    1.44
    //};
    1.41
    ]};
    1.40
    )};
    1.35
    Activations Density 0.120%

    No Known Activations