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. 24-GEMMASCOPE-RES-16K
    6. 1075
    Prev
    Next
    INDEX
    Explanations

    programming language keywords related to class definitions and inheritance

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

    Follows "extends" or ":" in code

    np_acts-logits-general · gemini-2.0-flash

    programming class inheritance

    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
     resourceCulture
    -0.63
    AndEndTag
    -0.54
    Sucesor
    -0.52
    OGND
    -0.52
     ModelExpression
    -0.49
    PropertyChanging
    -0.49
    iços
    -0.48
    CPtr
    -0.48
    autorest
    -0.48
    omiast
    -0.47
    POSITIVE LOGITS
    帖最后由
    0.46
     Cinnamon
    0.41
     صوتيه
    0.41
     Core
    0.39
     ode
    0.39
    뀐
    0.39
     Abbey
    0.39
     MonoBehaviour
    0.39
     Innoc
    0.39
     Luk
    0.39
    Activations Density 0.047%

    No Known Activations