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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 7673
    Prev
    Next
    INDEX
    Explanations

    introductory phrases or sections in technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.40
     with
    -0.38
     via
    -0.36
     as
    -0.36
     or
    -0.36
     von
    -0.34
    я
    -0.34
     filter
    -0.34
    μ
    -0.34
     for
    -0.34
    POSITIVE LOGITS
     незавершена
    0.98
    <bos>
    0.97
    SourceChecksum
    0.86
     فريبيس
    0.85
    ChildScrollView
    0.82
    httphttps
    0.81
    })()
    0.79
     مشين
    0.78
    setVerticalGroup
    0.77
     doInBackground
    0.76
    Activations Density 3.796%

    No Known Activations