© 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. 24-GEMMASCOPE-RES-16K
    11. 16082
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and arguments surrounding guilt and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows abstract nouns

    np_acts-logits-general · gemini-2.0-flash

    abstract arguments and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saurait
    -0.60
     venons
    -0.60
     avoient
    -0.59
     veille
    -0.59
     enfans
    -0.57
     autorité
    -0.55
     colorés
    -0.53
     chiare
    -0.53
     habet
    -0.52
     bonté
    -0.51
    POSITIVE LOGITS
     concept
    1.47
     syndrome
    1.46
     phenomenon
    1.37
     theory
    1.30
     scenario
    1.24
     idea
    1.22
     trope
    1.20
     hypothesis
    1.19
     thing
    1.17
     argument
    1.15
    Activations Density 0.765%

    No Known Activations