© 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. 20-GEMMASCOPE-RES-131K
    6. 27992
    Prev
    Next
    INDEX
    Explanations

    instances of the character ":" used to indicate sections or labels

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

    if clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bahía
    -0.55
    fromnode
    -0.51
    يكب
    -0.46
     inoxidable
    -0.45
    ngths
    -0.45
    setupUi
    -0.45
     IFTT
    -0.45
     "..\..\
    -0.44
     copias
    -0.43
    DockStyle
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.62
    WriteLiteral
    0.48
     Gu
    0.45
    Sorry
    0.42
    :
    0.41
     sorry
    0.40
     :
    0.40
     =
    0.40
    :].
    0.40
    Incomplete
    0.40
    Activations Density 0.004%

    No Known Activations