© 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. 31-GEMMASCOPE-RES-16K
    6. 2744
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "be," particularly in terms of honesty, clarity, and active engagement

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

    phrases where "be" is followed by an adjective or descriptive word to express a state or quality.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.62
    escaped
    -0.47
    Datuak
    -0.47
    ustimmung
    -0.46
     ExecuteAsync
    -0.46
    DockStyle
    -0.46
    Rüyada
    -0.45
    SourceChecksum
    -0.44
    kuš
    -0.44
    habitude
    -0.44
    POSITIVE LOGITS
     proactive
    0.64
     honest
    0.50
     flexible
    0.49
     creative
    0.46
     able
    0.44
     kasarigan
    0.43
     productive
    0.43
     part
    0.42
     assertive
    0.42
     patient
    0.41
    Activations Density 0.193%

    No Known Activations