© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 1220
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and operations

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

    numeric literals and numeric variable assignments 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
    ↵↵
    -0.44
    fjspx
    -0.36
    렀
    -0.31
     truly
    -0.30
    Theme
    -0.30
    ]';
    -0.28
     fre
    -0.28
     अर्
    -0.28
    TypeEnum
    -0.27
    ++];
    -0.27
    POSITIVE LOGITS
     ModelExpression
    0.91
     CreateTagHelper
    0.88
    OGND
    0.82
     كومونز
    0.82
     ब्रेकडाउन
    0.81
    Datuak
    0.79
     Roskov
    0.76
     فريبيس
    0.75
     defaultstate
    0.75
     يتيمه
    0.74
    Activations Density 1.149%

    No Known Activations