© 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. 24-GEMMASCOPE-RES-16K
    11. 595
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal implications and responsibilities

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

    Prepositions followed by articles or nouns

    np_acts-logits-general · gemini-2.0-flash

    prepositions followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.43
    Jegyzetek
    -0.41
    itemBuilder
    -0.37
    appspot
    -0.35
    setArguments
    -0.34
    JoinTable
    -0.34
     getItemId
    -0.34
     befolk
    -0.34
     fle
    -0.32
    staticmethod
    -0.32
    POSITIVE LOGITS
     виправивши
    0.63
    Билгалдахарш
    0.55
    parsedMessage
    0.53
    Vidite
    0.51
    OGND
    0.50
     <<<<<<<<<<<<<<
    0.50
     CanadaChoose
    0.49
    WriteLiteral
    0.49
     nahilalakip
    0.49
     Wikimedijinoj
    0.48
    Activations Density 1.067%

    No Known Activations