© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4359
    Prev
    Next
    INDEX
    Explanations

    references to housing programs, particularly those affecting families in rural areas and their accessibility to affordable options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.66
    timewa
    -0.53
     mergeFrom
    -0.53
    læg
    -0.49
     maquinaria
    -0.49
    Contro
    -0.49
    beli
    -0.48
     circon
    -0.48
     jadwal
    -0.48
     ventes
    -0.47
    POSITIVE LOGITS
     access
    0.63
    +#+#
    0.62
    accesso
    0.57
    __*/
    0.56
    ReusableCell
    0.56
     IndexError
    0.54
     otomatig
    0.54
    FontOfSize
    0.53
     Meksiku
    0.53
    UrlResolution
    0.52
    Activations Density 0.305%

    No Known Activations