© 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-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28169
    Prev
    Next
    INDEX
    Explanations

    occurrences of various numeric values and coordinates within programming or code-related contexts

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

    coordinates and graphics commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     विश्वसनीयता
    -0.57
    ècie
    -0.51
    ISSE
    -0.48
    яти
    -0.47
    INCE
    -0.47
     LNB
    -0.47
     defStyleAttr
    -0.46
    prin
    -0.46
    Rela
    -0.43
     simplifié
    -0.43
    POSITIVE LOGITS
    FontOfSize
    0.76
    TypedDataSet
    0.69
    principalColumn
    0.67
     transparence
    0.64
    MessageTagHelper
    0.62
     contemporaine
    0.61
    IntoConstraints
    0.59
    AxisAlignment
    0.59
    AutoScaleMode
    0.59
    InSection
    0.58
    Activations Density 0.053%

    No Known Activations