© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10610
    Prev
    Next
    INDEX
    Explanations

    specific terminology and concepts related to structured organizations or unions in a socio-political context

    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
    onAttach
    -0.63
    ftagPool
    -0.56
    EOR
    -0.54
     AspNetCore
    -0.52
     Vikipedi
    -0.51
    Xna
    -0.51
    bukkit
    -0.51
    PMailer
    -0.49
    aclk
    -0.45
    ober
    -0.44
    POSITIVE LOGITS
    ars
    1.18
    aries
    1.13
    ary
    1.13
    ARY
    1.04
    ár
    1.02
    ari
    1.01
    arios
    1.00
    aris
    0.97
    aria
    0.96
    arian
    0.96
    Activations Density 0.503%

    No Known Activations