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. 24-GEMMASCOPE-RES-16K
    6. 5424
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and conversation in the text

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

    Follows names of people or pets

    np_acts-logits-general · gemini-2.0-flash

    Spike and dialogue markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dis
    -0.31
     obstante
    -0.29
     besø
    -0.29
    навли
    -0.28
     cartaz
    -0.28
     visited
    -0.28
     admitted
    -0.28
     envió
    -0.28
    gång
    -0.28
    '][$
    -0.28
    POSITIVE LOGITS
     مشين
    0.72
    帖最后由
    0.60
    verifyException
    0.59
    UnusedPrivate
    0.58
    oredCriteria
    0.57
    AnimationsModule
    0.53
     rotate
    0.53
    SpringRunner
    0.51
    afficheront
    0.50
    
    0.50
    Activations Density 0.178%

    No Known Activations