© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4219
    Prev
    Next
    INDEX
    Explanations

    elements related to API responses and their handling

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

    "response" token

    np_acts-logits-general · gemini-2.0-flash

    response assignment or method call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ​​
    -0.59
    *
    -0.45
    Jag
    -0.43
    Mill
    -0.40
    At
    -0.40
    Usually
    -0.40
    <
    -0.40
    But
    -0.40
    Big
    -0.39
    Fer
    -0.39
    POSITIVE LOGITS
     response
    1.41
     Response
    1.35
    response
    1.25
    Response
    1.24
     RESPONSE
    1.22
     responses
    1.16
     Responses
    1.13
    RESPONSE
    1.13
    Responses
    1.06
    responses
    1.05
    Activations Density 0.102%

    No Known Activations