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. 16-GEMMASCOPE-RES-16K
    6. 5265
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses in text

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

    URLs starting with "www"

    np_acts-logits-general · gemini-2.0-flash

    urls

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     []:
    -0.74
    MessageTagHelper
    -0.70
    extAlignment
    -0.65
    fillType
    -0.63
    ::*;
    -0.61
     createSlice
    -0.61
     devrez
    -0.60
    RTHOOK
    -0.60
     MERCHANTABILITY
    -0.59
    ]}"
    -0.58
    POSITIVE LOGITS
     WWW
    0.99
    wwww
    0.93
    www
    0.90
     www
    0.85
    WWW
    0.83
    Www
    0.80
    wwwww
    0.80
    ww
    0.79
    WWWW
    0.72
    wwwwwwww
    0.70
    Activations Density 0.028%

    No Known Activations