© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9047
    Prev
    Next
    INDEX
    Explanations

    references to connectivity issues and technical specifications

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

    punctuation in lists, especially commas and semicolons separating items in an enumeration.

    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
    CloseOperation
    -0.49
    __':
    -0.39
    Einzelnachweise
    -0.39
    ;';
    -0.38
    ]]:
    -0.38
    :");
    -0.37
     muualla
    -0.37
    __":
    -0.37
    ();?>
    -0.37
    fromLTRB
    -0.36
    POSITIVE LOGITS
     typelib
    0.78
    LookAnd
    0.51
    httphttps
    0.50
     atardecer
    0.48
    цезда
    0.48
     Italijani
    0.47
    oa̍t
    0.46
     snippetHide
    0.44
     protoimpl
    0.44
    цездатний
    0.44
    Activations Density 0.386%

    No Known Activations