Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4192
    Prev
    Next
    INDEX
    Explanations

    verbs related to figuring things out or solving problems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Down
    -1.47
    Out
    -1.47
    Up
    -1.45
     Out
    -1.42
     Up
    -1.39
    Off
    -1.39
     Down
    -1.36
     Off
    -1.35
    OUT
    -1.32
    Away
    -1.32
    POSITIVE LOGITS
    aarrggbb
    0.50
    achelor
    0.48
     put
    0.48
    ImageField
    0.48
    clown
    0.47
    bitField
    0.47
     done
    0.46
     ours
    0.46
     vack
    0.46
     tf
    0.45
    Activations Density 0.246%

    No Known Activations