Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 11886
    Prev
    Next
    INDEX
    Explanations

    sequences that involve collecting or aggregating terms or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     purpoſe
    -0.58
     pleaſure
    -0.53
    ConstraintMaker
    -0.52
    GEBURTSDATUM
    -0.52
    Personendaten
    -0.52
     ſever
    -0.51
    tvguidetime
    -0.51
    rungsseite
    -0.50
     reaſon
    -0.49
     houſe
    -0.49
    POSITIVE LOGITS
     terms
    0.50
     term
    0.49
    ậc
    0.47
     inhoud
    0.44
     BorderSide
    0.44
    świ
    0.43
     composants
    0.41
    terms
    0.41
     Term
    0.40
     werkzaam
    0.40
    Activations Density 2.370%

    No Known Activations