© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5326
    Prev
    Next
    INDEX
    Explanations

    phrases and clauses that indicate time-related actions or sequences

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

    Comes before or after a verb/clause

    np_acts-logits-general · gemini-2.0-flash

    sequence followed by another

    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
     EconPapers
    -0.54
     Biôgrafia
    -0.46
    gatsby
    -0.45
    xdc
    -0.44
    StructEnd
    -0.44
     Perſ
    -0.42
     georg
    -0.42
     Houſe
    -0.42
     diver
    -0.40
    zzleHttp
    -0.40
    POSITIVE LOGITS
    complexContent
    0.56
    wijl
    0.52
     @"/
    0.52
     Grüsse
    0.47
    archiviato
    0.47
    brando
    0.46
     wobei
    0.44
     اینکه
    0.44
    voller
    0.43
     Numerade
    0.42
    Activations Density 0.385%

    No Known Activations