© 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. 14-GEMMASCOPE-RES-16K
    11. 13079
    Prev
    Next
    INDEX
    Explanations

    expressions of magnitude or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lähteet
    -0.89
    <_>
    -0.74
    migrationBuilder
    -0.63
     almeno
    -0.63
     gynhyrchwyd
    -0.60
     permanentes
    -0.59
    曖昧さ回避
    -0.57
    seamnă
    -0.56
     ledig
    -0.55
    já
    -0.54
    POSITIVE LOGITS
     מאוד
    0.67
     sekali
    0.64
     great
    0.64
     important
    0.60
     greatly
    0.59
     valuable
    0.59
     heavy
    0.58
     heavily
    0.58
     hugely
    0.57
    great
    0.56
    Activations Density 0.242%

    No Known Activations