Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14353
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain instructions, documentation, or references to tutorials and guides related to functionality or features

    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
     CURIAM
    -0.58
    ValueStyle
    -0.52
    يميديا
    -0.45
     MonoBehaviour
    -0.42
    astéroïdes
    -0.42
    rungsseite
    -0.40
    حوالہ
    -0.40
    endenza
    -0.39
     useRouter
    -0.39
    RTGC
    -0.38
    POSITIVE LOGITS
     guides
    0.77
    Guides
    0.70
     Guides
    0.67
     manuals
    0.67
     guide
    0.65
    guides
    0.61
     instructions
    0.61
    instructions
    0.60
     instruction
    0.60
     guidance
    0.59
    Activations Density 0.465%

    No Known Activations