© 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-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 2712
    Prev
    Next
    INDEX
    Explanations

    the word "It" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.99
    GEBURTSDATUM
    -0.98
     виправивши
    -0.97
     صوتيه
    -0.84
    Hentet
    -0.80
     Himo
    -0.79
    KommentareTeilen
    -0.77
    يكب
    -0.76
    principalColumn
    -0.76
     calendriers
    -0.76
    POSITIVE LOGITS
    xious
    0.72
    zelfde
    0.65
     certainly
    0.62
    kaç
    0.60
    ward
    0.59
    й
    0.59
    しかし
    0.58
    rededor
    0.57
    neath
    0.56
     therefore
    0.55
    Activations Density 0.268%

    No Known Activations