© 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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8748
    Prev
    Next
    INDEX
    Explanations

    code structures, particularly those related to function definitions and method calls

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

    function call expressions and method invocations in code.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArrowToggle
    -0.79
     يتيمه
    -0.74
    AddTagHelper
    -0.73
     Мексичка
    -0.72
    BufferException
    -0.65
    UnitTesting
    -0.65
     BytesLike
    -0.65
     كومونز
    -0.63
    MLLoader
    -0.62
     AspNetCore
    -0.62
    POSITIVE LOGITS
    ↵
    0.65
    ();}
    0.65
    }
    0.60
    .}
    0.60
    );}
    0.60
    </tbody>
    0.58
     }
    0.57
    });
    0.56
    ){}
    0.55
    <eos>
    0.54
    Activations Density 0.922%

    No Known Activations