© 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. 17-GEMMASCOPE-RES-16K
    6. 12821
    Prev
    Next
    INDEX
    Explanations

    concepts related to analysis and systematic evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poffible
    -0.78
     Majefty
    -0.73
    ſelf
    -0.73
     purpoſe
    -0.71
    ötzlich
    -0.71
     beſt
    -0.70
     pleaſure
    -0.69
    Kjelder
    -0.69
     censiti
    -0.69
    standers
    -0.69
    POSITIVE LOGITS
     that
    0.74
     of
    0.68
     consisting
    0.56
     similar
    0.54
     based
    0.53
    tagext
    0.53
     involving
    0.51
     worth
    0.51
     paio
    0.50
     similaires
    0.49
    Activations Density 1.465%

    No Known Activations