© 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. 5077
    Prev
    Next
    INDEX
    Explanations

    terms related to understanding or comprehension

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

    comprehension

    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
     Vars
    -0.53
     statisti
    -0.51
     Datos
    -0.49
     Pastoral
    -0.46
    dating
    -0.46
     Etik
    -0.45
     Otra
    -0.45
     privati
    -0.44
    Sak
    -0.44
    Tik
    -0.44
    POSITIVE LOGITS
     comprehension
    1.81
     Comprehension
    1.66
     comprehend
    1.65
     Compre
    1.48
     compre
    1.47
    Compre
    1.46
     comprehended
    1.45
     comprehen
    1.33
    prehension
    1.15
     compren
    1.11
    Activations Density 0.010%

    No Known Activations