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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7854
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly single and double quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.47
     CreateTagHelper
    -0.47
     ModelExpression
    -0.45
     referenties
    -0.38
     rep
    -0.37
    DebuggerStep
    -0.37
    ็จ
    -0.36
     Utilities
    -0.35
    ImageContext
    -0.35
    ̸
    -0.35
    POSITIVE LOGITS
    setVerticalGroup
    0.58
    cause
    0.55
    '''
    0.52
     '
    0.51
    """
    0.50
     "
    0.50
     „
    0.50
    Cause
    0.49
     "'
    0.47
    -“
    0.46
    Activations Density 0.375%

    No Known Activations