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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 55339
    Prev
    Next
    INDEX
    Explanations

    angle brackets, indicating generic types or templates in code

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

    template type names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.47
    })]
    -0.45
     }}$}
    -0.43
    );
    
    
    -0.42
     Syrie
    -0.41
     arrayList
    -0.40
    __))
    -0.39
    dataArray
    -0.39
    [];
    
    -0.38
     flesta
    -0.38
    POSITIVE LOGITS
     <
    1.78
     (<
    1.20
    (<
    1.05
     <\
    1.02
     $<
    0.96
     $<$
    0.91
     <.
    0.91
     "<
    0.88
    /<
    0.86
     <<
    0.84
    Activations Density 0.027%

    No Known Activations