© 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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 15816
    Prev
    Next
    INDEX
    Explanations

    technical terms and expressions related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wicidata
    -0.38
    见
    -0.35
    ★
    -0.34
     Sepul
    -0.34
    わ
    -0.34
    CRUD
    -0.33
     Italijanski
    -0.33
     LASER
    -0.33
     serial
    -0.32
    OGND
    -0.32
    POSITIVE LOGITS
     joint
    0.76
     jointly
    0.72
    ształ
    0.70
     gemeinsame
    0.69
    JOINT
    0.68
    joint
    0.68
     Joint
    0.63
     gemens
    0.62
     JOINT
    0.60
     gemeinsamen
    0.60
    Activations Density 1.238%

    No Known Activations