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-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9663
    Prev
    Next
    INDEX
    Explanations

    closing braces in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.83
    featureID
    -0.77
    SharedCtor
    -0.75
     Normdatei
    -0.74
     المعيارى
    -0.73
    StoryboardSegue
    -0.71
     autorytatywna
    -0.70
     transfieras
    -0.68
    writeFieldEnd
    -0.67
     nakalista
    -0.66
    POSITIVE LOGITS
    ↵↵
    0.57
    ↵
    0.50
    public
    0.49
    ↵↵↵
    0.47
    </h3>
    0.45
    <eos>
    0.43
     Speaking
    0.43
    Speaking
    0.42
    ↵↵↵↵
    0.41
    ↵↵↵↵↵
    0.41
    Activations Density 0.069%

    No Known Activations