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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4782
    Prev
    Next
    INDEX
    Explanations

    technical specifications and values related to data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /}.
    -0.56
    InvalidProtocol
    -0.53
    Level
    -0.49
     szint
    -0.45
    richTextPanel
    -0.45
     CGRectMake
    -0.45
    fromCharCode
    -0.45
     другому
    -0.43
     chiffres
    -0.43
     }}"
    -0.42
    POSITIVE LOGITS
     виправивши
    0.86
     تانيه
    0.71
     Normdatei
    0.69
     NUKAT
    0.65
    +:+
    0.65
    ArgsConstructor
    0.64
    RectangleBorder
    0.63
    TagMode
    0.63
     NgModule
    0.60
     незавершена
    0.60
    Activations Density 0.595%

    No Known Activations