Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5889
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate justifications or reasons

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

    Preceding words of "reason" or "reasons."

    np_acts-logits-general · gemini-2.0-flash

    foregoing reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.66
    MigrationBuilder
    -0.58
    sätzlich
    -0.51
    ########.
    -0.51
     المعيارى
    -0.51
     referenties
    -0.50
    Література
    -0.48
     estimés
    -0.46
    Билгалдахарш
    -0.46
     esternos
    -0.46
    POSITIVE LOGITS
     reason
    2.76
     reasons
    2.58
    reason
    2.23
     Reason
    2.12
    reasons
    2.12
     Reasons
    2.07
    Reason
    2.05
    Reasons
    1.94
     REASON
    1.94
     REASONS
    1.84
    Activations Density 0.460%

    No Known Activations