© 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. 116126
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology and variable identifiers

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

    variable assignments and declarations

    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
    WriteTagHelper
    -1.23
     noDo
    -1.16
     المعيارى
    -1.15
     Roskov
    -1.12
     kasarigan
    -1.11
    IUrlHelper
    -1.11
     Biôgrafia
    -1.10
    GEBURTSDATUM
    -1.09
    <unused3>
    -1.09
     Савезне
    -1.09
    POSITIVE LOGITS
    ,
    0.44
     =
    0.43
     (
    0.40
     is
    0.39
    .
    0.38
    )
    0.33
    :
    0.32
    L
    0.32
    er
    0.31
    C
    0.31
    Activations Density 0.021%

    No Known Activations