© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 12225
    Prev
    Next
    INDEX
    Explanations

    terms related to product specifications and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnknownFieldSet
    -0.65
     Préférences
    -0.64
    TypedDataSet
    -0.63
    )++;
    -0.61
    Portail
    -0.61
    reuil
    -0.59
     Audiodateien
    -0.58
    clusal
    -0.58
    DockStyle
    -0.58
    发表于
    -0.57
    POSITIVE LOGITS
    Viitteet
    0.50
    HomeAsUpEnabled
    0.47
     שוליים
    0.46
     Перейти
    0.44
     Meksiku
    0.44
     altres
    0.43
    ൾ
    0.43
     arac
    0.42
    集
    0.41
     Newmarket
    0.41
    Activations Density 0.130%

    No Known Activations