© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 93129
    Prev
    Next
    INDEX
    Explanations

    underscore-prefixed or underscore-contained elements, possibly indicating metadata or special properties in a programming context

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

    underscore prefixed code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    oredCriteria
    -0.71
    parsedMessage
    -0.66
    MessageOf
    -0.64
     CreateTagHelper
    -0.59
    transQ
    -0.59
     surla
    -0.56
     otomatig
    -0.52
    EndContext
    -0.51
    __':
    -0.50
     kaarangay
    -0.50
    POSITIVE LOGITS
     _
    0.67
    =_
    0.59
    ._
    0.56
    ('_
    0.52
    ("_
    0.52
    '_
    0.51
    (_
    0.51
    *_
    0.50
    ::_
    0.50
     "_
    0.49
    Activations Density 0.082%

    No Known Activations