© 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. 4-GEMMASCOPE-RES-16K
    6. 12592
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or importance related to various concepts or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.74
     препратки
    -0.71
    complexType
    -0.67
     BoxDecoration
    -0.65
    futbolista
    -0.64
     ویکی‌آمباردا
    -0.63
    quisite
    -0.62
    addContainerGap
    -0.60
     ModelExpression
    -0.58
    IntoConstraints
    -0.58
    POSITIVE LOGITS
    staticmethod
    0.60
    -------
    0.59
    featureID
    0.56
    äinen
    0.55
     estekak
    0.54
     šķ
    0.53
     lätt
    0.53
     temporales
    0.52
    لينكات
    0.52
     svårt
    0.51
    Activations Density 0.194%

    No Known Activations