© 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. 21-GEMMASCOPE-RES-16K
    6. 10871
    Prev
    Next
    INDEX
    Explanations

    conjunctions and their usage in lists or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.63
    parsedMessage
    -0.59
    GTCX
    -0.51
    Diweddarwch
    -0.51
     transfieras
    -0.49
    DataMember
    -0.49
    évaluateur
    -0.49
    IonicModule
    -0.48
    LLocation
    -0.48
    StoryboardSegue
    -0.47
    POSITIVE LOGITS
    rungsseite
    0.53
    .*")]
    0.46
    äjä
    0.41
    ())));
    0.37
    InSeconds
    0.37
     Packers
    0.36
    httphttps
    0.35
    (&:
    0.35
    "]));
    0.34
    ","");
    0.34
    Activations Density 0.390%

    No Known Activations