© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 7608
    Prev
    Next
    INDEX
    Explanations

    financial figures and references to auditing

    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
     pylint
    -0.60
    PYX
    -0.57
     cc
    -0.56
    Datuak
    -0.56
    Predecesor
    -0.55
    messageInfo
    -0.55
    Legături
    -0.51
    *-*-
    -0.51
     ligiloj
    -0.51
     estimés
    -0.50
    POSITIVE LOGITS
    ţe
    0.47
    min
    0.47
     insuffisamment
    0.46
    isEmail
    0.46
    DoubleQuotes
    0.46
    km
    0.45
    mol
    0.44
    Cllr
    0.44
    cmb
    0.44
     
    0.44
    Activations Density 0.621%

    No Known Activations