© 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. 8171
    Prev
    Next
    INDEX
    Explanations

    instances of "gram" which is related to bacterial classifications in scientific 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
    expandindo
    -0.47
     Bioaccumulative
    -0.44
    óticas
    -0.41
    Externé
    -0.40
    ፩
    -0.40
    ThroughAttribute
    -0.40
    raim
    -0.39
    اصله
    -0.38
     Kne
    -0.38
    ynchronously
    -0.38
    POSITIVE LOGITS
    gram
    0.95
     gram
    0.90
    Gram
    0.89
     mirror
    0.78
     Gram
    0.75
    GRAM
    0.71
    grams
    0.70
     GRAM
    0.66
     mirrors
    0.65
    mirror
    0.65
    Activations Density 0.245%

    No Known Activations