© 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. 27-GEMMASCOPE-RES-16K
    6. 9499
    Prev
    Next
    INDEX
    Explanations

    references to HTTP methods and associated actions in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Otro
    -0.33
    RTCK
    -0.31
     aceea
    -0.30
    ً
    -0.28
     nám
    -0.28
     câte
    -0.27
    elif
    -0.27
    Saiba
    -0.27
    やかに
    -0.27
    település
    -0.27
    POSITIVE LOGITS
     surla
    0.76
    ConstraintMaker
    0.65
     disponibilités
    0.61
    yntaxException
    0.61
    ArgsConstructor
    0.61
    findpost
    0.60
     Gegenteil
    0.60
    庁
    0.59
    HideFlags
    0.58
     विश्वसनीयता
    0.57
    Activations Density 3.321%

    No Known Activations