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. 12577
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or expressions relating to mechanics or physics

    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
    UrlResolution
    -0.80
    WireFormatLite
    -0.71
    EDEFAULT
    -0.61
    raszam
    -0.58
    новниш
    -0.57
    raszamy
    -0.56
    rungsseite
    -0.56
    ijão
    -0.55
    saraba
    -0.54
    Datuak
    -0.54
    POSITIVE LOGITS
    partial
    1.75
     partial
    1.49
    Partial
    1.27
     Partial
    1.26
    ∂
    1.13
    parti
    1.05
     parti
    1.04
     parcial
    1.01
    Parti
    0.92
     partially
    0.92
    Activations Density 0.472%

    No Known Activations