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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-GEMMASCOPE-RES-16K
    6. 238
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to court proceedings and inmate experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.59
     snippetHide
    -0.58
    stdc
    -0.55
    ècie
    -0.53
    ())->
    -0.48
     createSlice
    -0.47
     RVA
    -0.47
     Inga
    -0.46
    weza
    -0.44
    ogia
    -0.43
    POSITIVE LOGITS
     defendant
    1.70
     defendants
    1.63
     plaintiff
    1.37
     Defendant
    1.33
     respondent
    1.30
     respondents
    1.28
     plaintiffs
    1.27
    Defendant
    1.26
     Defendants
    1.26
    defendant
    1.24
    Activations Density 2.332%

    No Known Activations