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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8356
    Prev
    Next
    INDEX
    Explanations

    numerical values and constructors in programming code

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

    Code-related punctuation and keywords

    np_acts-logits-general · gemini-2.0-flash

    programming access modifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.81
    SharedDtor
    -0.61
    if
    -0.52
     TextAppearance
    -0.51
    oredCriteria
    -0.49
    ChildScrollView
    -0.47
    ((
    -0.47
     <=",
    -0.47
     consultato
    -0.47
     mandatario
    -0.47
    POSITIVE LOGITS
     public
    0.96
    public
    0.86
     private
    0.73
    protected
    0.71
    private
    0.70
    Initializable
    0.68
     privately
    0.67
     Public
    0.65
     öffentlich
    0.64
    XmlAccessType
    0.62
    Activations Density 0.040%

    No Known Activations