© 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. 18-GEMMASCOPE-RES-16K
    6. 6440
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions and usage rights in software licenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Permissions to copy, modify, and distribute

    np_acts-logits-general · gemini-2.0-flash

    license, permission, consent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MessageBoxIcon
    -0.58
     solution
    -0.53
    asymp
    -0.52
    rxjs
    -0.52
     NSCoder
    -0.51
    copa
    -0.51
     box
    -0.51
    AsUp
    -0.50
    intios
    -0.48
     IMO
    -0.47
    POSITIVE LOGITS
    ftagPool
    0.69
    IntoConstraints
    0.67
     ModelExpression
    0.63
     <>",
    0.59
     initComponents
    0.57
     createState
    0.57
    ErrUnexpectedEOF
    0.54
    исленность
    0.53
    icator
    0.49
     referenties
    0.49
    Activations Density 0.037%

    No Known Activations