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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 12751
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions related to arrival or return

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

    Referring to returning or being home

    np_acts-logits-general · gemini-2.0-flash

    coming home

    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
    ">//
    -0.87
    udesta
    -0.59
    principalColumn
    -0.59
    RTLD
    -0.59
    awtextra
    -0.56
    setVerticalGroup
    -0.54
     FontWeight
    -0.53
    InjectAttribute
    -0.53
    offsetTop
    -0.52
    upsi
    -0.52
    POSITIVE LOGITS
     home
    4.41
    home
    3.60
     HOME
    3.10
    Home
    3.09
     Home
    3.06
    HOME
    2.84
     hjem
    2.45
     thuis
    2.39
     hogar
    2.34
     homes
    2.31
    Activations Density 0.382%

    No Known Activations