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. 0-GEMMASCOPE-RES-16K
    6. 9916
    Prev
    Next
    INDEX
    Explanations

    references to toys and playthings, particularly with an emphasis on their function in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.80
     ExecuteAsync
    -0.70
    ostante
    -0.64
     transfieras
    -0.63
    Composable
    -0.63
    :✨
    -0.62
     Monfieur
    -0.62
     ostavi
    -0.61
     ProtoMessage
    -0.60
    EndTag
    -0.59
    POSITIVE LOGITS
     toys
    0.62
    face
    0.58
     Zimbabwe
    0.58
     sandwich
    0.53
     intentionally
    0.53
     Aeros
    0.52
     stringBy
    0.50
    noinspection
    0.50
    ResponseStatus
    0.50
     dro
    0.49
    Activations Density 0.079%

    No Known Activations