© 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. 24-GEMMASCOPE-RES-16K
    11. 15931
    Prev
    Next
    INDEX
    Explanations

    pronouns and words related to individual and collective identity

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

    certainty or affirmation

    np_acts-logits-general · gemini-2.0-flash

    certainly, definitely, undoubtedly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.69
    JKLM
    -0.63
    GOTREF
    -0.63
    tdessen
    -0.61
     viewType
    -0.58
     maging
    -0.57
    ::::::::
    -0.56
    tagHelperRunner
    -0.56
    NoSuchAlgorithm
    -0.56
     Chriſt
    -0.56
    POSITIVE LOGITS
     certainly
    3.06
     definitely
    2.91
     surely
    2.66
     undoubtedly
    2.61
    certainly
    2.56
     Certainly
    2.47
     obviously
    2.42
    Certainly
    2.40
    definitely
    2.28
    Definitely
    2.22
    Activations Density 0.535%

    No Known Activations