© 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. 13906
    Prev
    Next
    INDEX
    Explanations

    details related to craftsmanship and effort in the creation process

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

    Attention to detail

    np_acts-logits-general · gemini-2.0-flash

    attention to detail and care

    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
    adpleegd
    -0.53
    IBOutlet
    -0.52
    spesies
    -0.51
    Portail
    -0.50
    onAttach
    -0.48
    ంట
    -0.48
    erol
    -0.46
    PhysRevLett
    -0.46
    примеча
    -0.46
     tarvit
    -0.45
    POSITIVE LOGITS
     meticulous
    1.55
     attention
    1.51
     detail
    1.33
     careful
    1.32
     care
    1.29
    attention
    1.27
     Attention
    1.27
     Careful
    1.21
     precision
    1.20
    Attention
    1.20
    Activations Density 0.215%

    No Known Activations