© 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. 12-GEMMASCOPE-RES-16K
    6. 3228
    Prev
    Next
    INDEX
    Explanations

    references to recent time periods and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    batore
    -0.59
     springfox
    -0.57
    wpi
    -0.55
    oodle
    -0.55
    programme
    -0.55
    ⟬
    -0.55
    zzleHttp
    -0.54
    ohjel
    -0.52
     EDA
    -0.52
     Audiodateien
    -0.51
    POSITIVE LOGITS
     last
    1.41
    last
    1.39
     Last
    1.35
    Last
    1.31
     LAST
    1.21
    getLast
    1.15
     getLast
    1.10
    LAST
    1.09
    setLast
    1.05
     Dernière
    0.93
    Activations Density 0.077%

    No Known Activations