© 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. 40-GEMMASCOPE-RES-16K
    6. 5333
    Prev
    Next
    INDEX
    Explanations

    numerical representations, particularly related to identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ninety
    -0.76
     Ninety
    -0.72
     ninth
    -0.60
     Eighty
    -0.59
     eighty
    -0.59
     eighties
    -0.58
     CreateTagHelper
    -0.58
     &___
    -0.57
     Administrativna
    -0.56
     Ninth
    -0.56
    POSITIVE LOGITS
    4
    0.63
    5
    0.56
    3
    0.54
    6
    0.47
    2
    0.40
    homonymie
    0.35
    enumii
    0.34
    7
    0.31
    NUMX
    0.31
     ciudadana
    0.30
    Activations Density 0.173%

    No Known Activations