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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12204
    Prev
    Next
    INDEX
    Explanations

    mentions of formal written communications or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
    cassert
    -0.57
     absoluto
    -0.56
     onPostExecute
    -0.56
     اسلامی
    -0.55
     orgull
    -0.55
     كمان
    -0.54
     saites
    -0.54
     informée
    -0.54
    ertor
    -0.53
    esterday
    -0.52
    POSITIVE LOGITS
    head
    0.72
    bootstrapcdn
    0.63
     digress
    0.60
     letters
    0.59
    SequentialGroup
    0.59
    Letters
    0.58
    kenny
    0.57
     writers
    0.56
     writer
    0.55
     Letters
    0.55
    Activations Density 0.119%

    No Known Activations