© 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. 4808
    Prev
    Next
    INDEX
    Explanations

    specific references to choices and options that individuals can select from

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

    choices or options

    np_acts-logits-general · gemini-2.0-flash

    choice or choosing

    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
    VertexAttrib
    -0.50
    انجليز
    -0.47
     мәкал
    -0.46
    ExtendWith
    -0.45
     mergeFrom
    -0.44
     Winaray
    -0.43
    ModelSerializer
    -0.43
     poveznice
    -0.43
    eddings
    -0.43
    RTEE
    -0.43
    POSITIVE LOGITS
     choice
    3.25
     choose
    3.13
     choosing
    3.07
     chooses
    2.88
    choose
    2.79
     Choice
    2.77
     Choosing
    2.74
    choice
    2.74
     Choose
    2.72
     chose
    2.71
    Activations Density 0.597%

    No Known Activations