© 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. 23-GEMMASCOPE-RES-16K
    6. 2144
    Prev
    Next
    INDEX
    Explanations

    elements related to citations and references in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delwed
    -0.38
     Obrador
    -0.35
     assisti
    -0.35
     Verr
    -0.34
    fer
    -0.34
     Signals
    -0.33
     оригіналу
    -0.33
     Honest
    -0.33
    pellier
    -0.32
    Saman
    -0.32
    POSITIVE LOGITS
    脚注の使い方
    0.83
     '\\;'
    0.71
     CreateTagHelper
    0.69
    AndEndTag
    0.63
     informée
    0.57
    parsedMessage
    0.57
    ⤹
    0.56
    :✨
    0.52
     مرئيه
    0.52
    Cyfarwyddwr
    0.51
    Activations Density 0.129%

    No Known Activations