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. 12637
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and procedural issues, particularly in the context of appeals and convictions

    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
     lisäksi
    -0.70
     sauvages
    -0.68
     religieuses
    -0.66
     asupra
    -0.65
    seamnă
    -0.62
     fallu
    -0.61
     colorés
    -0.61
     aveug
    -0.61
    kenalkan
    -0.61
     jotka
    -0.60
    POSITIVE LOGITS
    “-
    0.88
    +#+#
    0.84
    ²-
    0.74
    ’-
    0.66
    »-
    0.64
    EndContext
    0.64
    ”-
    0.62
    DataAnnotations
    0.61
    providedIn
    0.59
    "-
    0.58
    Activations Density 1.556%

    No Known Activations