© 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. 24-GEMMASCOPE-RES-16K
    6. 1456
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, particularly sibling connections

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

    Family members, especially siblings

    np_acts-logits-general · gemini-2.0-flash

    brother, sister, member, neighbor

    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
    IGraphics
    -0.47
    RunAsync
    -0.43
    Климат
    -0.42
    ()")
    -0.42
     kaynağından
    -0.41
    ::_('
    -0.41
    wußt
    -0.40
    Geplaatst
    -0.40
    AndEndTag
    -0.40
    OrWhiteSpace
    -0.39
    POSITIVE LOGITS
     Brother
    0.84
     Neighbor
    0.81
    Brother
    0.81
    Neighbor
    0.80
     member
    0.79
     BROTHER
    0.79
    Sister
    0.79
     brother
    0.78
     neighbor
    0.77
     Sister
    0.77
    Activations Density 0.188%

    No Known Activations