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. 21-GEMMASCOPE-RES-16K
    6. 15267
    Prev
    Next
    INDEX
    Explanations

    information related to wildfire incidents and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.71
    ScopeManager
    -0.64
     ProtoMessage
    -0.60
    +#+#
    -0.59
    发表于
    -0.58
    uver
    -0.55
     referenties
    -0.53
    providedIn
    -0.52
    topt
    -0.51
     Skye
    -0.51
    POSITIVE LOGITS
     Stanis
    0.69
     Sacramento
    0.68
     Modesto
    0.61
     Sacra
    0.59
     Sac
    0.59
     houſe
    0.59
    رشف
    0.58
    Sacramento
    0.58
     Merced
    0.58
     Stockton
    0.58
    Activations Density 0.176%

    No Known Activations