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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 1377
    Prev
    Next
    INDEX
    Explanations

    patterns related to film reviews and awards

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

    Tokens preceding titles or names

    np_acts-logits-general · gemini-2.0-flash

    proper nouns and technical terms

    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
    <unused63>
    -0.51
     A
    -0.50
     
    -0.48
     K
    -0.47
     V
    -0.47
     B
    -0.46
    んだよね
    -0.45
     S
    -0.44
     T
    -0.43
     $\
    -0.43
    POSITIVE LOGITS
    Geplaatst
    1.16
     HasFactory
    1.14
    تقاوى
    1.13
    mybatisplus
    1.12
    ագրություններ
    1.10
    bootstrapcdn
    1.10
    Portale
    1.07
    AutoScaleMode
    1.05
     autorytatywna
    1.04
     NSCoder
    1.02
    Activations Density 0.475%

    No Known Activations