© 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. 7-GEMMASCOPE-RES-16K
    6. 3024
    Prev
    Next
    INDEX
    Explanations

    unique attributes or characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.68
     censura
    -0.65
    <em>
    -0.62
    стма
    -0.57
    <code>
    -0.57
    FieldDescriptor
    -0.54
    ber
    -0.53
     filmes
    -0.53
     prakti
    -0.52
     devriez
    -0.52
    POSITIVE LOGITS
     unique
    1.64
     UNIQUE
    1.63
     Unique
    1.60
    unique
    1.58
    Unique
    1.55
     uniqueness
    1.54
    UNIQUE
    1.53
     uniques
    1.52
     uniqu
    1.41
    UniqueId
    1.39
    Activations Density 0.060%

    No Known Activations