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. 24-GEMMASCOPE-RES-16K
    6. 15213
    Prev
    Next
    INDEX
    Explanations

    specific references to soccer players and their performance statistics

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

    Prepositions or helping verbs

    np_acts-logits-general · gemini-2.0-flash

    to followed by verb

    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
    InSection
    -0.49
     gynhyrchwyd
    -0.47
     Outcome
    -0.46
    ͞
    -0.46
     Resultados
    -0.45
     Fue
    -0.45
    DX
    -0.45
    кей
    -0.44
    Rok
    -0.43
     ::=
    -0.42
    POSITIVE LOGITS
    ThroughAttribute
    0.65
    UrlResolution
    0.64
    PullParser
    0.62
     troubled
    0.60
     kaarangay
    0.60
    MENAFN
    0.59
    ніципалі
    0.59
    BorderFactory
    0.58
     troubling
    0.57
    DeleteBehavior
    0.55
    Activations Density 0.101%

    No Known Activations