© 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. 27-GEMMASCOPE-RES-16K
    6. 9979
    Prev
    Next
    INDEX
    Explanations

    the word "a" and its variations in different contexts

    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
     nahilalakip
    -0.49
     kaupung
    -0.48
    ญิง
    -0.45
    MethodManager
    -0.44
     verksam
    -0.44
     valsty
    -0.44
     trasparente
    -0.43
     kunjungan
    -0.42
     måske
    -0.41
     stratégique
    -0.41
    POSITIVE LOGITS
     bummer
    0.55
     boon
    0.54
     bit
    0.53
     veritable
    0.53
     joaat
    0.51
    exact
    0.49
     tad
    0.49
    complished
    0.49
     hindrance
    0.47
     nuisance
    0.47
    Activations Density 0.386%

    No Known Activations