© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1721
    Prev
    Next
    INDEX
    Explanations

    codes related to error handling and data processing

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

    Code or programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    Ctrl followed by quote or matter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '},
    
    -0.86
    };
    
    -0.79
    ?}
    -0.78
    }
    
    -0.76
    "}
    -0.76
    }</
    -0.74
    }");
    -0.72
    .)}
    -0.72
    }`
    -0.71
    "});
    -0.71
    POSITIVE LOGITS
    URLException
    0.68
    RegressionTest
    0.61
     الدولى
    0.60
     FBref
    0.60
     ImportError
    0.57
    LLocation
    0.56
     Baillargeon
    0.55
     Italijani
    0.54
    NameValuePair
    0.53
    jíma
    0.53
    Activations Density 0.014%

    No Known Activations