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. 8682
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to negligence

    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
    IntentFilter
    -0.54
     ((*
    -0.53
    sizeCache
    -0.52
    ckpt
    -0.50
     negotiate
    -0.50
    GIVEREF
    -0.49
    ztály
    -0.47
     ['./
    -0.46
    プローチ
    -0.46
     defaultstate
    -0.45
    POSITIVE LOGITS
     adipis
    0.75
    Lorem
    0.75
     consectetur
    0.72
     amet
    0.69
     dolor
    0.66
     dolore
    0.64
     ipsum
    0.62
    LookAnd
    0.58
     eius
    0.58
    lorem
    0.56
    Activations Density 0.132%

    No Known Activations