© 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. 2555
    Prev
    Next
    INDEX
    Explanations

    terms related to analytical frameworks or systematic categorization in research contexts

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

    followed by suffixes like "ias", "isms", "ings"

    np_acts-logits-general · gemini-2.0-flash

    endings for certain concepts

    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
     يتيمه
    -0.79
     Normdatei
    -0.59
    vantaged
    -0.56
    nologia
    -0.55
     complètes
    -0.53
     مرئيه
    -0.51
     παιδιά
    -0.51
     adulte
    -0.51
    Normdaten
    -0.50
     relâche
    -0.50
    POSITIVE LOGITS
     مشين
    0.69
    EndGlobalSection
    0.69
     utafitiHapana
    0.65
    tagHelper
    0.60
    httphttps
    0.59
    esses
    0.58
    ments
    0.56
    LayoutConstraint
    0.56
    RenderAtEndOf
    0.56
    titudes
    0.56
    Activations Density 0.235%

    No Known Activations