© 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. 18-GEMMASCOPE-RES-16K
    11. 1692
    Prev
    Next
    INDEX
    Explanations

    references to statistical functions and their associated components in a programming context

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

    Code, paths, or indexes

    np_acts-logits-general · gemini-2.0-flash

    technical terms and code filenames

    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
     originaux
    -0.66
     suivants
    -0.61
     récents
    -0.60
     blessés
    -0.55
     készült
    -0.55
     soorten
    -0.55
     jeunesse
    -0.53
     financière
    -0.53
     számára
    -0.52
     actuels
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    0.96
    ніципалі
    0.96
     utafitiHapana
    0.90
    LookAnd
    0.89
    UnusedPrivate
    0.84
     '{@
    0.83
    ")));
    0.81
    \|^{
    0.80
    ########.
    0.80
    >';
    0.79
    Activations Density 0.309%

    No Known Activations