© 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. 665
    Prev
    Next
    INDEX
    Explanations

    instances of the word "full" and related phrases indicating completeness or entirety

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

    the word "full" followed by another word or phrase.

    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
     kasarigan
    -0.47
     ligiloj
    -0.40
    <bos>
    -0.38
    __(/*!
    -0.36
    Sedangkan
    -0.36
    joi
    -0.34
    azioni
    -0.34
    ace
    -0.34
     melhorar
    -0.34
    ajo
    -0.34
    POSITIVE LOGITS
     Full
    1.10
     FULL
    1.06
     full
    1.02
    Full
    0.96
    FULL
    0.92
    full
    0.88
    フル
    0.84
     полно
    0.79
     pleins
    0.79
     fuller
    0.78
    Activations Density 0.117%

    No Known Activations