© 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. 121750
    Prev
    Next
    INDEX
    Explanations

    discussions of evaluation and feedback on experiences or studies

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

    strengths and limitations

    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
     مشين
    -0.58
    principalColumn
    -0.56
     متعلقه
    -0.48
     Bourgoin
    -0.48
     <<<<<<<<<<<<<<
    -0.48
     ProductService
    -0.47
     IBOutlet
    -0.47
    \{\\
    -0.45
     Numerade
    -0.45
     wireType
    -0.44
    POSITIVE LOGITS
    Strengths
    0.51
     strengths
    0.49
    umque
    0.48
     challenges
    0.45
     limitations
    0.44
     Strengths
    0.42
     meille
    0.42
     peculiarities
    0.41
     retos
    0.41
    fficiencies
    0.41
    Activations Density 0.033%

    No Known Activations