© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11300
    Prev
    Next
    INDEX
    Explanations

    sections of the document that contain formatting or structural elements, such as lines or separators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.74
     odkazy
    -0.73
     typelib
    -0.70
     nahilalakip
    -0.69
    tvguidetime
    -0.68
     оригіналу
    -0.68
    OGND
    -0.68
    PerformLayout
    -0.66
    toggler
    -0.64
    RetentionPolicy
    -0.64
    POSITIVE LOGITS
    alagi
    0.48
     ferons
    0.46
    haj
    0.44
     kor
    0.41
     hit
    0.41
     }^{(
    0.41
    ofern
    0.40
     Hama
    0.40
     wichtig
    0.40
    Sklici
    0.40
    Activations Density 0.825%

    No Known Activations