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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 1096
    Prev
    Next
    INDEX
    Explanations

    specific references to version identifiers and management within coding or documentation contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The letter "V"

    np_acts-logits-general · gemini-2.0-flash

    V or v followed by specific characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sere
    -0.53
     socc
    -0.53
     "").
    -0.51
    textcolor
    -0.51
    GeneratedMessage
    -0.48
     appro
    -0.47
     toán
    -0.47
    )](
    -0.47
     nakalista
    -0.46
    en
    -0.46
    POSITIVE LOGITS
     V
    0.79
    V
    0.76
    jsdelivr
    0.73
     iprot
    0.72
    v
    0.70
     v
    0.70
    getV
    0.70
     Normdatei
    0.68
     AdapterView
    0.63
     alimentaires
    0.63
    Activations Density 0.173%

    No Known Activations