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

    Neuronpedia

    APICircuit 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. 10168
    Prev
    Next
    INDEX
    Explanations

    themes related to expression and representation of identity and experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    clientY
    -0.59
    unov
    -0.52
    prava
    -0.51
    หาร
    -0.51
    िल्म
    -0.50
    meros
    -0.50
    來的
    -0.49
    Werke
    -0.48
    Obrázky
    -0.47
    acie
    -0.47
    POSITIVE LOGITS
     how
    0.72
    ValueStyle
    0.68
     собой
    0.68
     esternos
    0.62
     صوتيه
    0.61
    SharedDtor
    0.60
     what
    0.60
    atorship
    0.59
    ]")]
    0.58
    rrggbb
    0.58
    Activations Density 0.386%

    No Known Activations