© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13263
    Prev
    Next
    INDEX
    Explanations

    the concept of rarity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AxisAlignment
    -0.64
    IActionResult
    -0.61
     StatelessWidget
    -0.58
    ReusableCell
    -0.57
    ScopeManager
    -0.56
    GroupLayout
    -0.56
    RenderAtEndOf
    -0.55
     ſind
    -0.54
     صوتيه
    -0.54
     afl
    -0.53
    POSITIVE LOGITS
     rare
    1.52
    Rare
    1.37
     Rare
    1.33
    rare
    1.33
     rarest
    1.21
     RARE
    1.09
     rarity
    1.07
     rarer
    1.06
     Rarely
    0.98
     rares
    0.97
    Activations Density 0.095%

    No Known Activations