© 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. 5313
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific measurement and experimentation

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

    after "the"/ "a" / "of"

    np_acts-logits-general · gemini-2.0-flash

    the followed by descriptive nouns

    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
     برانيه
    -0.40
     asp
    -0.36
     Dim
    -0.34
     ag
    -0.34
     lead
    -0.33
    fore
    -0.32
     إ
    -0.32
    RTEE
    -0.31
     dim
    -0.31
     Eub
    -0.31
    POSITIVE LOGITS
    الحياه
    0.69
    MethodManager
    0.66
     الرياضيه
    0.59
    IntoConstraints
    0.58
    ifikationer
    0.57
    WebElementEntity
    0.57
    makeConstraints
    0.56
     kasarigan
    0.55
     Normdatei
    0.54
    awtextra
    0.54
    Activations Density 1.539%

    No Known Activations