Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5698
    Prev
    Next
    INDEX
    Explanations

    code syntax elements and structures

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

    Code-related punctuation

    np_acts-logits-general · gemini-2.0-flash

    duality and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    EndGlobal
    -0.51
     gynhyrchwyd
    -0.48
    四人
    -0.47
    四大
    -0.43
    secuted
    -0.42
     relâche
    -0.41
     pairwise
    -0.40
     Puls
    -0.40
    دانشنامهٔ
    -0.40
     羽
    -0.40
    POSITIVE LOGITS
     begge
    0.76
     Beide
    0.73
     beide
    0.72
     båda
    0.71
     Both
    0.69
     both
    0.67
     entrambi
    0.66
     ambos
    0.65
     keduanya
    0.64
    Both
    0.63
    Activations Density 1.421%

    No Known Activations