© 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. 20-GEMMASCOPE-RES-131K
    6. 27961
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and research contexts, specifically focusing on cells, their interactions, and experimental outcomes

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

    technical and scientific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })();
    
    -0.36
     Lower
    -0.35
    Lower
    -0.31
    ổi
    -0.31
     Photocase
    -0.30
    KURZBESCHREIBUNG
    -0.30
     slik
    -0.30
    เข
    -0.29
    })()
    -0.29
     rock
    -0.28
    POSITIVE LOGITS
     transférez
    0.67
    TypedDataSet
    0.61
     CanadaChoose
    0.59
     mergeFrom
    0.56
    TestingModule
    0.54
     transfieras
    0.54
     CreateTagHelper
    0.53
    fromnode
    0.51
     orgánico
    0.50
    
    0.50
    Activations Density 0.430%

    No Known Activations