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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3062
    Prev
    Next
    INDEX
    Explanations

    curly braces and parentheses, indicating object or function definitions in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code delimiters or brackets

    np_acts-logits-general · gemini-2.0-flash

    JSON objects and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    קישורים
    -0.74
    Diwedd
    -0.71
     transfieras
    -0.70
    migrationBuilder
    -0.69
    хьтан
    -0.68
     väx
    -0.67
    PreExecute
    -0.67
     AssemblyProduct
    -0.67
     iſt
    -0.66
    abestanden
    -0.65
    POSITIVE LOGITS
    ↵
    1.14
    },{
    0.82
    ↵↵
    0.71
    }>;
    0.69
     };
    0.68
    })
    
    0.65
     },
    0.62
    }));
    0.60
    },
    
    0.60
    }),
    0.60
    Activations Density 0.104%

    No Known Activations