© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7969
    Prev
    Next
    INDEX
    Explanations

    phrases that imply uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -0.85
    ientras
    -0.84
    Personendaten
    -0.83
     Monfieur
    -0.82
     avoient
    -0.82
     onCreateView
    -0.81
     informée
    -0.79
     protoimpl
    -0.79
    parsedMessage
    -0.76
     pouvoit
    -0.74
    POSITIVE LOGITS
     potentially
    0.69
     (
    0.63
     and
    0.63
     
    0.60
     barely
    0.58
     beyond
    0.58
    ,
    0.58
     in
    0.57
     outside
    0.57
     >=
    0.57
    Activations Density 0.388%

    No Known Activations