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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6994
    Prev
    Next
    INDEX
    Explanations

    long sequences of whitespace characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -1.25
    Obrázky
    -1.24
    })`
    -1.21
    SourceChecksum
    -1.20
    ########.
    -1.17
    ⓧ
    -1.10
     <=",
    -1.09
    principalTable
    -1.08
    aarrggbb
    -1.07
    contentLoaded
    -1.07
    POSITIVE LOGITS
     he
    0.55
     in
    0.48
     
    0.39
    /
    0.39
     with
    0.39
     (
    0.38
     fall
    0.38
     transfer
    0.38
     will
    0.37
     e
    0.35
    Activations Density 0.126%

    No Known Activations