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. 11-GEMMASCOPE-RES-16K
    6. 8282
    Prev
    Next
    INDEX
    Explanations

    numeric values and their relationships in data contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.78
    LookAnd
    -0.71
     noDo
    -0.69
    RenderAtEndOf
    -0.67
    iffance
    -0.63
    DeleteBehavior
    -0.62
     BoxFit
    -0.62
     ब्रेकडाउन
    -0.61
    InputBorder
    -0.59
     صوتيه
    -0.58
    POSITIVE LOGITS
     year
    0.51
    s
    0.49
     fjor
    0.48
    年
    0.46
     года
    0.44
     period
    0.44
     год
    0.43
     годом
    0.42
     Erde
    0.41
     року
    0.41
    Activations Density 0.361%

    No Known Activations