Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2767
    Prev
    Next
    INDEX
    Explanations

    instances of the word "roll" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.53
     المعيارى
    -0.53
    دانشنامهٔ
    -0.50
    HomeAsUpEnabled
    -0.49
    PageIndex
    -0.46
    InjectAttribute
    -0.44
     bezeichneter
    -0.44
    AutoScaleMode
    -0.44
    igshid
    -0.41
     estekak
    -0.40
    POSITIVE LOGITS
     roll
    1.55
     Roll
    1.37
    roll
    1.31
    Roll
    1.30
     ROLL
    1.25
    ROLL
    1.20
     rol
    1.17
     rolling
    1.16
     scroll
    1.09
     Rol
    1.09
    Activations Density 0.226%

    No Known Activations