© 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. 10-GEMMASCOPE-RES-16K
    6. 15442
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations related to organizations and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.53
    iconque
    -0.46
    mybatisplus
    -0.46
    ỡng
    -0.42
    rrggbb
    -0.41
    lwjgl
    -0.41
    :✨
    -0.39
    jmniej
    -0.39
    offsetof
    -0.39
    nsito
    -0.37
    POSITIVE LOGITS
    ⓧ
    0.61
    ParallelGroup
    0.47
    Revenir
    0.44
    WillAppear
    0.44
    RTCK
    0.42
     defaultstate
    0.42
    ########.
    0.38
     attending
    0.38
     Attending
    0.38
     дописавши
    0.38
    Activations Density 0.751%

    No Known Activations