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. 21-GEMMASCOPE-RES-16K
    6. 900
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to secure shell (SSH) operations and key management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.81
    Tembelea
    -0.74
    AndEndTag
    -0.71
     CreateTagHelper
    -0.69
    ագրություններ
    -0.66
    parsedMessage
    -0.64
    ClientSize
    -0.63
    存于互联网档案馆
    -0.62
     nakalista
    -0.60
    RTGC
    -0.60
    POSITIVE LOGITS
     shell
    0.66
    Shell
    0.62
    Bash
    0.60
     environmental
    0.60
    bash
    0.59
     Shell
    0.59
     variables
    0.58
    zsh
    0.58
     перемен
    0.57
     Environment
    0.56
    Activations Density 0.525%

    No Known Activations