© 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. 9-GEMMASCOPE-RES-16K
    11. 10929
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to image processing and descriptor methods

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

    distance or metric calculations

    np_acts-logits-general · gemini-2.0-flash

    distance metric and threshold

    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
    ftagPool
    -0.60
     disambiguazione
    -0.59
    ScopeManager
    -0.54
     informée
    -0.54
    CharacterOffset
    -0.52
    WebElementEntity
    -0.49
    ropriate
    -0.48
    -------------</
    -0.48
     CreateTagHelper
    -0.47
    tagPool
    -0.47
    POSITIVE LOGITS
    \|^{
    0.40
    kmeans
    0.40
    PasswordEncoder
    0.39
     Clustering
    0.39
     rép
    0.36
     distance
    0.36
     BorderSide
    0.36
    Rep
    0.36
     clustering
    0.35
     medlem
    0.35
    Activations Density 1.125%

    No Known Activations