© 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. 10-GEMMASCOPE-RES-16K
    6. 12066
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terms related to proteins, memory structures, and classification frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.84
    complexContent
    -0.80
    MemoryWarning
    -0.78
    HomeAsUpEnabled
    -0.70
    PerformLayout
    -0.64
    ressee
    -0.63
    ніципа
    -0.62
     chi̍t
    -0.60
     itemprop
    -0.58
    unhofer
    -0.57
    POSITIVE LOGITS
    ([]
    0.50
    Dal
    0.48
    Rohy
    0.47
     statistiques
    0.47
    jsko
    0.46
    imo
    0.46
     @"/
    0.46
    deelte
    0.45
     blessures
    0.45
     discorso
    0.45
    Activations Density 0.646%

    No Known Activations