© 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. 23-GEMMASCOPE-RES-16K
    6. 2184
    Prev
    Next
    INDEX
    Explanations

    significant concepts or themes in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.57
    TypedDataSet
    -0.57
    rungsseite
    -0.54
    出版年
    -0.53
     henvisninger
    -0.52
    uxxxx
    -0.49
    setViewportView
    -0.49
    apimachinery
    -0.49
    +#+
    -0.49
     noDo
    -0.48
    POSITIVE LOGITS
     worth
    0.52
    worth
    0.48
     worthwhile
    0.45
     worthy
    0.44
     Worth
    0.42
     WORTH
    0.41
    Worth
    0.40
    worthy
    0.38
     deserving
    0.38
    SwitchCompat
    0.37
    Activations Density 0.347%

    No Known Activations