© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 6043
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and uncertainties in context

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

    "if not" followed by "all", "any", or "ever"

    np_acts-logits-general · gemini-2.0-flash

    if not any

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vitae
    -0.38
     esmeralda
    -0.38
    '))
    -0.37
    话
    -0.36
     demikian
    -0.36
     inoxydable
    -0.36
     initComponents
    -0.35
    eraard
    -0.35
    __':
    -0.35
    voort
    -0.35
    POSITIVE LOGITS
    Personendaten
    0.59
    GEBURTSDATUM
    0.52
    RegressionTest
    0.51
    Datuak
    0.47
    دانشنامهٔ
    0.46
    EndContext
    0.45
    новниш
    0.43
    UserScript
    0.42
    Grass
    0.42
     Devin
    0.40
    Activations Density 0.683%

    No Known Activations