© 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. 40-GEMMASCOPE-RES-16K
    6. 6094
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching for and identifying people or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DeleteBehavior
    -0.58
     Observed
    -0.49
    دانشنامهٔ
    -0.49
    parsedMessage
    -0.48
    ngdoc
    -0.48
    observed
    -0.43
    esez
    -0.43
    Observed
    -0.43
    SBATCH
    -0.43
    jmniej
    -0.42
    POSITIVE LOGITS
     looking
    2.55
     seeking
    1.98
    looking
    1.96
    Looking
    1.84
     searching
    1.84
     Looking
    1.83
     LOOKING
    1.78
    LOOKING
    1.58
     lookin
    1.54
    seeking
    1.48
    Activations Density 0.501%

    No Known Activations