© 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. 24-GEMMASCOPE-RES-16K
    6. 7834
    Prev
    Next
    INDEX
    Explanations

    technical specifications and considerations related to shaders and image processing effects

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

    sound or video effects options

    np_acts-logits-general · gemini-2.0-flash

    effects or filters

    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
    期刊论文
    -0.59
    ILayout
    -0.56
    messageInfo
    -0.56
    futbolista
    -0.55
    viewBox
    -0.54
     tartalomajánló
    -0.54
     mah
    -0.52
    солю
    -0.50
    WriteBarrier
    -0.50
     useAppContext
    -0.50
    POSITIVE LOGITS
     effects
    1.15
     Effects
    1.05
     effect
    1.01
    Effects
    0.97
    effects
    0.92
    effect
    0.90
     EFFECTS
    0.88
     Effect
    0.87
     filters
    0.86
     effets
    0.83
    Activations Density 0.280%

    No Known Activations