© 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. 31-GEMMASCOPE-RES-16K
    6. 9730
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and conjunctions in sentences

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

    commas that appear at the end of clauses or before conjunctions in complex sentences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itself
    -0.43
    along
    -0.41
    舺
    -0.41
    ,
    -0.40
    之一
    -0.40
     itself
    -0.40
     themselves
    -0.40
     افتراض
    -0.38
     along
    -0.38
    themselves
    -0.38
    POSITIVE LOGITS
    ConstraintMaker
    0.58
    setVerticalGroup
    0.55
     OFDb
    0.55
    endpush
    0.45
     виправивши
    0.44
    Personensuche
    0.43
    RepeatedField
    0.42
     kasarigan
    0.42
     weil
    0.41
     مرئيه
    0.41
    Activations Density 0.087%

    No Known Activations