© 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. 13-GEMMASCOPE-RES-16K
    6. 8558
    Prev
    Next
    INDEX
    Explanations

    expressions indicating analysis or evaluation of systems and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.57
    InputModule
    -0.47
    AutoScale
    -0.44
    RTSC
    -0.44
     Lordship
    -0.44
    webElement
    -0.43
    SEB
    -0.43
     ब्रेकडाउन
    -0.43
    Toponymie
    -0.43
    keyColumn
    -0.42
    POSITIVE LOGITS
    Rujukan
    0.39
    laterra
    0.35
     Fe
    0.34
     numerus
    0.33
    ❉
    0.33
    czegó
    0.32
     istore
    0.31
    これも
    0.31
    こちらも
    0.31
    csolódó
    0.30
    Activations Density 1.090%

    No Known Activations