© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 58168
    Prev
    Next
    INDEX
    Explanations

    code-related terms and structures specific to programming functions and data handling

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

    code fields and messages

    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
    parsedMessage
    -0.73
    ंदीखरीदारी
    -0.71
     AttributeSet
    -0.69
     ब्रेकडाउन
    -0.69
    WriteTagHelper
    -0.66
    ьаж
    -0.66
    principalColumn
    -0.66
    GEBURTSDATUM
    -0.66
    ParallelGroup
    -0.65
    LookAnd
    -0.65
    POSITIVE LOGITS
    OneToOne
    0.52
     front
    0.36
    станов
    0.35
    ManyToOne
    0.34
    rätt
    0.34
     vertes
    0.34
    getSupport
    0.33
     contracted
    0.33
     Ehe
    0.32
    zogen
    0.32
    Activations Density 0.027%

    No Known Activations