© 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. 24-GEMMASCOPE-RES-16K
    6. 5265
    Prev
    Next
    INDEX
    Explanations

    references to evidence and claims regarding legal or ethical matters

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

    "evidence" or proof

    np_acts-logits-general · gemini-2.0-flash

    asserting truth or evidence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.58
     anticipates
    -0.44
     fieldNum
    -0.42
     nahilalakip
    -0.41
     anticipating
    -0.41
    ématiques
    -0.41
     Photocase
    -0.41
     ADAPT
    -0.41
     anticipate
    -0.41
     adap
    -0.40
    POSITIVE LOGITS
     evidence
    0.68
     preuves
    0.64
    evidence
    0.64
     corroborated
    0.59
     credibility
    0.59
     Evidence
    0.59
    Evidence
    0.57
     Beweis
    0.57
    证据
    0.56
     credence
    0.56
    Activations Density 1.023%

    No Known Activations