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. 8-GEMMASCOPE-RES-16K
    6. 8174
    Prev
    Next
    INDEX
    Explanations

    phrases related to client satisfaction and business success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.76
     and
    -0.62
    -
    -0.59
    gi
    -0.57
     when
    -0.55
    _
    -0.54
    .
    -0.54
    py
    -0.53
    y
    -0.52
    u
    -0.52
    POSITIVE LOGITS
    ſelves
    1.18
    Personendaten
    1.17
    tvguidetime
    1.16
    ſelf
    1.16
     itſelf
    1.15
     Jefus
    1.12
     Houſe
    1.07
     myſelf
    1.07
     Monfieur
    1.04
     Efq
    1.02
    Activations Density 0.679%

    No Known Activations