© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 45631
    Prev
    Next
    INDEX
    Explanations

    terms related to factors in biochemical and molecular contexts

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

    nuclear factor kappa B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inghouse
    -0.50
    ]!='
    -0.49
    writing
    -0.46
    emptyList
    -0.45
     Acoustic
    -0.44
    OGND
    -0.43
     siang
    -0.42
    gib
    -0.42
     Greenwich
    -0.42
     Barber
    -0.42
    POSITIVE LOGITS
     factor
    2.22
     Factor
    2.17
    Factor
    2.09
    factor
    2.08
     FACTOR
    1.87
     factors
    1.72
    FACTOR
    1.68
     Factors
    1.62
    factors
    1.55
    Factors
    1.54
    Activations Density 0.035%

    No Known Activations