© 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. 4077
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and substitutions in equations

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

    Replacing or inserting values

    np_acts-logits-general · gemini-2.0-flash

    substitute into equations

    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
    protoc
    -0.62
    lccn
    -0.57
    انيف
    -0.54
    ArrowToggle
    -0.53
    mybatisplus
    -0.52
    providedIn
    -0.52
     esternos
    -0.52
    HideFlags
    -0.51
    DoubleQuotes
    -0.51
     Schatz
    -0.50
    POSITIVE LOGITS
     substitution
    1.24
     Substituting
    1.22
     substituted
    1.21
     substituting
    1.21
     substitutions
    1.17
     substitute
    1.09
    Substituting
    1.05
     Substitution
    1.01
     substitutes
    1.01
    Substitution
    1.00
    Activations Density 0.534%

    No Known Activations