Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 11684
    Prev
    Next
    INDEX
    Explanations

    sentences featuring the pronoun "I."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    koľvek
    -0.40
     posibles
    -0.39
    WebMethod
    -0.38
     mergeFrom
    -0.38
     hof
    -0.37
     intrig
    -0.36
     hitherto
    -0.36
    idu
    -0.36
     intervening
    -0.36
    ällor
    -0.35
    POSITIVE LOGITS
     guess
    1.84
     Guess
    1.46
    guess
    1.45
    Guess
    1.35
     suppose
    1.30
     think
    1.11
     guessing
    1.05
     guesses
    1.04
     supposes
    1.00
     glaube
    0.93
    Activations Density 0.274%

    No Known Activations