© 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. 38-GEMMASCOPE-RES-16K
    6. 8403
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare, gaming, and literary works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.98
     disambiguazione
    -0.81
    expandindo
    -0.77
    Jîn
    -0.77
    Билгалдахарш
    -0.75
     utafitiHapana
    -0.75
     auroit
    -0.75
    tvguidetime
    -0.75
    fjspx
    -0.73
     autorytatywna
    -0.72
    POSITIVE LOGITS
    ting
    0.44
    ers
    0.42
    ing
    0.31
    ⎨
    0.30
    .*")]
    0.30
    ERS
    0.28
    处
    0.28
    gs
    0.28
    IA
    0.28
    ային
    0.27
    Activations Density 1.117%

    No Known Activations