© 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. 18-GEMMASCOPE-RES-16K
    11. 1613
    Prev
    Next
    INDEX
    Explanations

    references to "frames" in various contexts

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

    "frame" and its variations

    np_acts-logits-general · gemini-2.0-flash

    frame and frameless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DispatchToProps
    -0.78
     Ahh
    -0.73
    LikeLiked
    -0.71
    JspWriter
    -0.69
    getSystemService
    -0.68
     Pingback
    -0.68
    новништво
    -0.68
     Majefty
    -0.68
     OnInit
    -0.67
    первых
    -0.67
    POSITIVE LOGITS
     frames
    1.27
     Frames
    1.22
     Frame
    1.14
    frames
    1.13
    Frames
    1.11
     FRAME
    1.10
     frame
    1.09
    frame
    1.00
    Frame
    0.98
    FRAME
    0.98
    Activations Density 0.104%

    No Known Activations