© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13744
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate assumptions or expectations about certain situations

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

    acceptance or assumption

    np_acts-logits-general · gemini-2.0-flash

    assumed to be true

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    errHandler
    -0.49
    ArrowToggle
    -0.47
     مشين
    -0.46
    MessageTagHelper
    -0.45
     informée
    -0.45
    ⤹
    -0.45
    OGND
    -0.45
    Portail
    -0.44
    NameInMap
    -0.44
    Carriera
    -0.43
    POSITIVE LOGITS
     unquestion
    0.93
     assumed
    0.93
     assumption
    0.88
    当たり前
    0.85
    assumed
    0.83
     assume
    0.79
     assumptions
    0.76
    assumption
    0.76
     accepted
    0.73
     certainty
    0.70
    Activations Density 0.441%

    No Known Activations