© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7273
    Prev
    Next
    INDEX
    Explanations

    specific actions related to evaluation and confirmation in scientific contexts

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

    phrases introducing an explanation, demonstration, or verification of a concept.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    essoa
    -0.44
    entibus
    -0.43
     confession
    -0.42
    hanging
    -0.42
    ambién
    -0.41
    Pesquisa
    -0.41
    Symbolic
    -0.40
    COMING
    -0.38
     вікісторінку
    -0.38
     COMING
    -0.38
    POSITIVE LOGITS
    
    0.59
    httphttps
    0.52
    tagHelperRunner
    0.52
    +#+#
    0.50
    #
    0.49
    RTSC
    0.48
    GraphicsUnit
    0.44
    InjectAttribute
    0.44
    UserScript
    0.43
     defaultstate
    0.42
    Activations Density 0.437%

    No Known Activations