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. 28-GEMMASCOPE-RES-16K
    6. 7827
    Prev
    Next
    INDEX
    Explanations

    technical terms related to connectivity and device management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after specific terms: connection, commitment, one

    np_acts-logits-general · gemini-2.0-flash

    connection to, commitment to, directly to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.38
     CURIAM
    -0.36
    </thead>
    -0.34
    </
    -0.33
      
    -0.32
     iota
    -0.32
     
    -0.32
    __((
    -0.32
     
    -0.31
    〕
    -0.31
    POSITIVE LOGITS
     nahilalakip
    0.73
     pouvoit
    0.63
     typelib
    0.62
     beginnetje
    0.62
     discorso
    0.60
    SharedDtor
    0.60
     Infór
    0.59
     increí
    0.59
    msgTypes
    0.57
    utilisons
    0.56
    Activations Density 0.029%

    No Known Activations