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. 24-GEMMASCOPE-RES-16K
    6. 2351
    Prev
    Next
    INDEX
    Explanations

    references to criteria, prerequisites, or specifications in a structured context

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

    "following"

    np_acts-logits-general · gemini-2.0-flash

    introduces a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    地看着
    -0.57
     оригіналу
    -0.54
    ddots
    -0.53
    ')['
    -0.53
    tymologie
    -0.53
    rboles
    -0.52
    Somehow
    -0.52
     másik
    -0.52
    KommentareTeilen
    -0.52
     Somehow
    -0.51
    POSITIVE LOGITS
     following
    3.82
    following
    3.32
     Following
    2.86
    Following
    2.74
     FOLLOWING
    2.73
     siguientes
    2.53
     seguenti
    2.40
     seguinte
    2.38
     siguiente
    2.35
     folgenden
    2.23
    Activations Density 0.827%

    No Known Activations