© 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. 15708
    Prev
    Next
    INDEX
    Explanations

    words related to games

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

    "game"

    np_acts-logits-general · gemini-2.0-flash

    game followed by descriptive words

    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
     CreateTagHelper
    -0.80
     ujednoznacz
    -0.65
    ValueGeneration
    -0.61
     defStyle
    -0.58
    ✭
    -0.58
    Gemini
    -0.58
    swire
    -0.57
     propOrder
    -0.57
    สึก
    -0.55
    MigrationBuilder
    -0.54
    POSITIVE LOGITS
    plan
    0.75
     changer
    0.74
    changer
    0.70
    changers
    0.64
    day
    0.60
    modes
    0.59
    cocks
    0.59
    plays
    0.59
     chang
    0.58
    boy
    0.55
    Activations Density 0.074%

    No Known Activations