© 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. 3-GEMMASCOPE-RES-16K
    11. 2006
    Prev
    Next
    INDEX
    Explanations

    advisory or obligatory statements regarding actions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gruber
    -0.64
     Affiliations
    -0.63
     mData
    -0.61
    opsida
    -0.61
     langt
    -0.60
     Engle
    -0.60
     bangs
    -0.59
    unknownFields
    -0.58
    сій
    -0.58
    PyExc
    -0.57
    POSITIVE LOGITS
     should
    2.88
     Should
    2.54
    should
    2.47
     SHOULD
    2.43
    Should
    2.38
    hould
    2.18
     shouldn
    1.91
     ought
    1.86
     shouldnt
    1.64
     sollte
    1.63
    Activations Density 0.077%

    No Known Activations