© 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. 18-GEMMASCOPE-RES-16K
    11. 2869
    Prev
    Next
    INDEX
    Explanations

    phrases that evaluate or describe qualities of experiences, performances, or objects

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

    that intensify adjectives

    np_acts-logits-general · gemini-2.0-flash

    adjective intensifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    これらの
    -0.49
     popolare
    -0.48
    <eos>
    -0.46
     θέ
    -0.46
     tasche
    -0.45
     Constitucional
    -0.45
     compositeur
    -0.45
    <bos>
    -0.44
     littéraire
    -0.44
    The
    -0.44
    POSITIVE LOGITS
    EDEFAULT
    0.90
    verwijspagina
    0.79
    afficheront
    0.75
     للاسماء
    0.74
    PreferredItem
    0.74
     Lightboxes
    0.74
    )$}
    0.74
    ]$}
    0.73
    ContentAsync
    0.73
    $")
    0.72
    Activations Density 0.592%

    No Known Activations