© 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. 28-GEMMASCOPE-RES-16K
    6. 7611
    Prev
    Next
    INDEX
    Explanations

    actions involving destruction and survival in a narrative context

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

    Preceding "by," "Return," or "layer"

    np_acts-logits-general · gemini-2.0-flash

    iced by, return 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
     المعيارى
    -0.71
     queſta
    -0.62
     surla
    -0.60
     ModelExpression
    -0.59
    LabelTagHelper
    -0.59
     allAfrica
    -0.58
    chieht
    -0.57
    styleType
    -0.56
     wireType
    -0.55
    الحياه
    -0.54
    POSITIVE LOGITS
    AddTagHelper
    0.51
    setVerticalGroup
    0.47
    RTEE
    0.43
    imageshack
    0.40
    ↵↵↵
    0.40
     <<<<<<<<<<<<<<
    0.40
    awtextra
    0.40
     Италијани
    0.39
    .";
    0.38
     때문
    0.38
    Activations Density 3.942%

    No Known Activations