© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 3107
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing moral implications and personal consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.82
    providedIn
    -0.79
    __":
    -0.74
    __':
    -0.71
    viewDidLoad
    -0.69
    MigrationBuilder
    -0.66
    __":
    -0.62
    __':
    -0.62
     MainAxisSize
    -0.61
     صوتيه
    -0.60
    POSITIVE LOGITS
     if
    3.54
    if
    2.37
     jika
    2.35
     если
    2.33
     nếu
    2.30
     dacă
    2.27
     hvis
    2.17
     якщо
    2.08
     ако
    1.95
     jeśli
    1.91
    Activations Density 2.139%

    No Known Activations