© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 10025
    Prev
    Next
    INDEX
    Explanations

    references to experimental methods and analyses

    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
    featureID
    -0.59
    balenciaga
    -0.55
    glLoadIdentity
    -0.54
    shadowOpacity
    -0.53
    WindowConstants
    -0.53
     nhau
    -0.51
    Themen
    -0.50
    GenerationType
    -0.50
    enumii
    -0.50
    glTexCoord
    -0.49
    POSITIVE LOGITS
    migrationBuilder
    0.72
    ItemBackground
    0.70
     investigation
    0.65
     surveys
    0.64
     preliminary
    0.63
     examination
    0.63
     survey
    0.63
     analysis
    0.62
     investigations
    0.62
    Ane
    0.61
    Activations Density 1.713%

    No Known Activations