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. 4-GEMMASCOPE-RES-16K
    6. 10972
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of radiation detection and optical phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.56
     مشين
    -0.55
    ография
    -0.53
    orghini
    -0.48
    offsetof
    -0.48
     intptr
    -0.48
    書館
    -0.47
    Erreferentziak
    -0.47
    клопе
    -0.47
    glPopMatrix
    -0.47
    POSITIVE LOGITS
     sunlight
    0.74
     rays
    0.71
     beam
    0.70
     photons
    0.69
    ctrons
    0.69
     rainwater
    0.67
     electricity
    0.66
     protons
    0.66
     varargin
    0.66
     methane
    0.62
    Activations Density 1.203%

    No Known Activations