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. 22-GEMMASCOPE-RES-16K
    6. 10322
    Prev
    Next
    INDEX
    Explanations

    elements related to television programming and broadcasting dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "host" or "hosts" appearing in text

    np_acts-logits-general · gemini-2.0-flash

    hosts and show personalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.53
    Према
    -0.53
     nobis
    -0.50
     betaling
    -0.50
     indipendente
    -0.48
     termen
    -0.48
     fuite
    -0.48
     solidarité
    -0.48
     paziente
    -0.47
    CppMethod
    -0.47
    POSITIVE LOGITS
     host
    2.23
     hosts
    2.06
     Host
    1.95
     Hosts
    1.84
    host
    1.81
    Host
    1.79
     hosting
    1.78
     HOST
    1.69
    Hosts
    1.68
    hosts
    1.66
    Activations Density 0.297%

    No Known Activations