© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 4615
    Prev
    Next
    INDEX
    Explanations

    Java import statements and the presence of package declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     private
    -0.46
    parsedMessage
    -0.46
     Gloria
    -0.44
    Gloria
    -0.43
     preside
    -0.43
     self
    -0.42
    achios
    -0.42
    略
    -0.41
    ldr
    -0.41
    તા
    -0.41
    POSITIVE LOGITS
    fasterxml
    1.00
    google
    0.89
    amazonaws
    0.89
    squareup
    0.78
    badlogic
    0.75
    bumptech
    0.74
    baomidou
    0.72
    alibaba
    0.72
    ScopeManager
    0.70
     незавершена
    0.69
    Activations Density 0.081%

    No Known Activations