© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 5063
    Prev
    Next
    INDEX
    Explanations

    terms related to user account verification and privacy settings

    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
    原始内容存档于
    -0.63
    ]='\
    -0.57
     consultato
    -0.55
    +#+#
    -0.54
     initComponents
    -0.53
    HashSet
    -0.50
    τογραφ
    -0.47
     Gefähr
    -0.46
    ühm
    -0.46
    ologically
    -0.45
    POSITIVE LOGITS
    gimento
    0.60
    ishment
    0.58
    ization
    0.56
    isation
    0.56
    ICATION
    0.55
    cimento
    0.55
    ylation
    0.55
    corporation
    0.54
    ITATION
    0.54
    রণ
    0.53
    Activations Density 0.205%

    No Known Activations