© 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. 10-GEMMASCOPE-RES-16K
    6. 7696
    Prev
    Next
    INDEX
    Explanations

    references to instances, actions, or conditions that require further clarification or elaboration

    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
    ########.
    -0.63
    RTEE
    -0.59
     Chwiliwch
    -0.55
     Signalez
    -0.54
     Roskov
    -0.51
     دیکھیے
    -0.51
    SequentialGroup
    -0.50
    fromnode
    -0.49
    :+:
    -0.49
    featureID
    -0.49
    POSITIVE LOGITS
    schutz
    0.44
    arschu
    0.41
    asă
    0.39
     jota
    0.38
    ciera
    0.38
     Osna
    0.37
    glLoad
    0.36
     stifled
    0.36
    Zunanje
    0.36
     Kassen
    0.36
    Activations Density 9.660%

    No Known Activations