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. 27-GEMMASCOPE-RES-16K
    6. 9555
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direction or movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extranjero
    -0.35
     armonía
    -0.35
    nucleus
    -0.34
     veille
    -0.34
    uset
    -0.34
    praš
    -0.34
    ลง
    -0.33
     έχ
    -0.33
    Brussels
    -0.33
     zachod
    -0.33
    POSITIVE LOGITS
    findpost
    0.64
     surla
    0.63
     referrerpolicy
    0.60
    principalColumn
    0.59
    rungsseite
    0.54
     lenker
    0.53
    hematical
    0.52
     Référence
    0.51
    #+#
    0.50
     defaultstate
    0.50
    Activations Density 0.076%

    No Known Activations