© 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. 5-GEMMASCOPE-RES-16K
    6. 426
    Prev
    Next
    INDEX
    Explanations

    Java components and classes related to Android development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.82
    omock
    -0.80
    ?";
    -0.75
    ResumeLayout
    -0.75
    Personendaten
    -0.75
     ComVisible
    -0.74
     calldata
    -0.73
    ValueStyle
    -0.73
    migrationBuilder
    -0.72
    styleType
    -0.71
    POSITIVE LOGITS
    aterdag
    0.51
    databinding
    0.50
    cstdlib
    0.48
    multer
    0.46
    JPanel
    0.43
     שוליים
    0.42
    cmath
    0.42
    UserScript
    0.41
    sstream
    0.40
    TargetException
    0.40
    Activations Density 0.032%

    No Known Activations