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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2155
    Prev
    Next
    INDEX
    Explanations

    specific scientific and medical processes or phenomena related to cell behavior and conditions affecting health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chaik
    -0.64
    hyrchwyd
    -0.55
    KURZBESCHREIBUNG
    -0.54
    MessageTagHelper
    -0.53
    ględ
    -0.51
    PreAuthorize
    -0.51
    mended
    -0.50
    WithIOException
    -0.50
     Administrativna
    -0.49
     itp
    -0.49
    POSITIVE LOGITS
     called
    3.52
    called
    2.89
     Called
    2.58
     llamado
    2.54
     CALLED
    2.53
    Called
    2.46
     known
    2.44
     llamada
    2.38
     chamado
    2.27
     named
    2.22
    Activations Density 1.329%

    No Known Activations