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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 6065
    Prev
    Next
    INDEX
    Explanations

    emotional and descriptive details related to characters and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getItemCount
    -0.65
    脚注の使い方
    -0.63
    ngOnInit
    -0.59
     Campan
    -0.57
     AttributeSet
    -0.56
     zelfs
    -0.56
    endphp
    -0.55
     PRD
    -0.55
    styleable
    -0.54
    MLLoader
    -0.54
    POSITIVE LOGITS
    ROGEN
    0.54
     Chwiliwch
    0.53
    TagHelper
    0.53
    არ
    0.51
    ENSIVE
    0.49
    谓
    0.48
    ífero
    0.48
    πον
    0.48
     bar
    0.48
     partial
    0.47
    Activations Density 0.579%

    No Known Activations