© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2294
    Prev
    Next
    INDEX
    Explanations

    terms related to biological taxonomy, specifically subspecies and species classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.66
    tagHelperRunner
    -0.54
     snippetHide
    -0.51
    Personendaten
    -0.49
     ostavi
    -0.47
    MLLoader
    -0.46
    NameInMap
    -0.46
     ſte
    -0.45
     contextLoads
    -0.44
    PerformLayout
    -0.40
    POSITIVE LOGITS
    ordeel
    0.45
    udayaan
    0.45
    VersionUID
    0.44
     perlas
    0.43
    eniging
    0.42
     especies
    0.42
     albicans
    0.42
     vayas
    0.42
     Spez
    0.42
     mijne
    0.41
    Activations Density 0.467%

    No Known Activations