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. 8700
    Prev
    Next
    INDEX
    Explanations

    specific symbols, characters, and technical terms often associated with programming or programming languages

    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
    RUnlock
    -0.56
    rinfo
    -0.50
    ỡng
    -0.48
    AddTagHelper
    -0.44
     متعلقه
    -0.42
    Obrázky
    -0.41
    ReusableCell
    -0.41
    RunAsync
    -0.40
     defaultstate
    -0.40
     SDLK
    -0.39
    POSITIVE LOGITS
    તિ
    0.65
    ત્ર
    0.58
    ઢ
    0.55
    ક્
    0.55
    ણી
    0.54
    સ્
    0.54
    મા
    0.54
    લી
    0.53
    તી
    0.49
    કા
    0.49
    Activations Density 1.355%

    No Known Activations