© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10570
    Prev
    Next
    INDEX
    Explanations

    elements related to user interface components in code

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

    Code, card, or mark-related vocabulary

    np_acts-logits-general · gemini-2.0-flash

    card game and UI elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indígen
    -0.75
     itſelf
    -0.75
     témoig
    -0.73
    ðsíða
    -0.73
     increí
    -0.70
     myſelf
    -0.70
     purpoſe
    -0.70
     '\\;'
    -0.69
    <unused8>
    -0.68
     estadounid
    -0.68
    POSITIVE LOGITS
    发表于
    0.30
    '
    0.26
    antd
    0.25
    .
    0.25
     det
    0.24
    <eos>
    0.24
    ,
    0.24
    console
    0.24
     te
    0.23
    package
    0.23
    Activations Density 0.235%

    No Known Activations