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. 23-GEMMASCOPE-RES-16K
    6. 9049
    Prev
    Next
    INDEX
    Explanations

    references to host keys and file access in the context of SSH configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NUKAT
    -0.48
     arşivlendi
    -0.48
    LEncoder
    -0.45
    oustics
    -0.42
    anguages
    -0.42
     brano
    -0.42
     laiko
    -0.42
     Konz
    -0.41
    .~(\
    -0.41
    另一
    -0.41
    POSITIVE LOGITS
     passim
    0.79
     thirteen
    0.79
     eighty
    0.79
     nineteen
    0.79
     thirty
    0.75
     forty
    0.72
     sixty
    0.71
     nine
    0.70
     twelve
    0.70
     fourteen
    0.70
    Activations Density 1.085%

    No Known Activations