© 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. 14219
    Prev
    Next
    INDEX
    Explanations

    verbs related to making or doing actions

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

    French words or legal related terms

    np_acts-logits-general · gemini-2.0-flash

    legal actions and outcomes

    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
    adpleegd
    -0.63
    osoba
    -0.59
    InstanceState
    -0.53
     leia
    -0.51
    xaml
    -0.49
    providedIn
    -0.49
     pinulongan
    -0.48
     <<<<<<<<<<<<<<
    -0.47
    SuspendLayout
    -0.46
    UVWXYZ
    -0.46
    POSITIVE LOGITS
     الرياضيه
    0.69
     autorytatywna
    0.61
    ]{\
    0.61
     Administrativna
    0.56
    preuve
    0.55
     appel
    0.54
    Ehrungen
    0.49
    bzero
    0.49
     homage
    0.49
    новниш
    0.48
    Activations Density 0.108%

    No Known Activations