© 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. 3295
    Prev
    Next
    INDEX
    Explanations

    references and citations in text

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

    HTML or technical markup characters like brackets, references, and links.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered 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
     queſta
    -0.59
     <=",
    -0.57
     transfieras
    -0.56
    UserScript
    -0.53
     IFTT
    -0.52
     BoxFit
    -0.52
     estekak
    -0.52
     Phry
    -0.51
    MethodManager
    -0.51
    WriteTagHelper
    -0.50
    POSITIVE LOGITS
     مشين
    0.43
     виправивши
    0.42
     heureux
    0.41
     confirmó
    0.41
     enfance
    0.40
     usarlo
    0.38
     dAtA
    0.38
     heureuse
    0.38
     confirmado
    0.38
     potvr
    0.38
    Activations Density 0.035%

    No Known Activations