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. 5670
    Prev
    Next
    INDEX
    Explanations

    terms related to temporary solutions or arrangements

    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
    UnusedPrivate
    -0.62
    Scrolled
    -0.55
     CreateTagHelper
    -0.53
    UpInside
    -0.53
    KeySpec
    -0.51
    Général
    -0.51
    ohjel
    -0.50
     homozygous
    -0.50
    iolis
    -0.50
    олові
    -0.49
    POSITIVE LOGITS
     temporary
    3.35
    temporary
    2.87
     Temporary
    2.82
     temporarily
    2.78
    Temporary
    2.71
     temporaire
    2.40
    tempor
    2.33
     Tempor
    2.26
     tijde
    2.25
     tempor
    2.12
    Activations Density 0.457%

    No Known Activations