Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 107070
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "public" related to method declarations in programming

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

    public method 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
     betweenstory
    -0.48
    ésult
    -0.37
     faſt
    -0.36
     continúa
    -0.34
     deſt
    -0.33
     onStart
    -0.33
    anskje
    -0.31
    todas
    -0.30
    xAA
    -0.30
     delà
    -0.30
    POSITIVE LOGITS
    public
    1.26
     public
    0.96
     Public
    0.88
    Public
    0.88
     PUBLIC
    0.77
    ublic
    0.75
     doInBackground
    0.73
    Hochspringen
    0.72
    UBLIC
    0.71
    UnusedPrivate
    0.71
    Activations Density 0.015%

    No Known Activations