Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 693
    Prev
    Next
    INDEX
    Explanations

    terms related to health risks and medical conditions

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

    biological and medical research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AndEndTag
    -0.60
    Enllaços
    -0.56
     հղումներ
    -0.50
    帖最后由
    -0.50
    endregion
    -0.48
     betweenstory
    -0.47
    Спољашње
    -0.46
    Bakgrunnsstoff
    -0.46
     something
    -0.45
     Basically
    -0.44
    POSITIVE LOGITS
     translateY
    0.43
    然而
    0.43
     efficacious
    0.42
     valueForKey
    0.40
    近年来
    0.40
     paradig
    0.38
     concurrently
    0.37
     ſind
    0.37
     stakeholders
    0.37
     pourtant
    0.36
    Activations Density 1.018%

    No Known Activations