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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2948
    Prev
    Next
    INDEX
    Explanations

    mentions of natural environments and geographical features

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    805
    +0.17
    0.7%
    1870
    +0.15
    0.6%
    1133
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    805
    +0.17
    0.03
    1133
    +0.15
    0.02
    1272
    +0.13
    0.01
    Negative Logits
     Pued
    -0.61
     Ceux
    -0.59
     surpl
    -0.56
     contribue
    -0.55
     exti
    -0.54
     viciss
    -0.53
     prolon
    -0.53
     reaf
    -0.52
    Доброго
    -0.52
     brille
    -0.52
    POSITIVE LOGITS
     landscape
    1.30
     Landscape
    1.19
    Landscape
    1.18
     landscapes
    1.14
    landscape
    1.14
     LANDSCAPE
    1.01
     Landscapes
    0.78
    terrain
    0.73
     landscaping
    0.70
     terrain
    0.70
    Activations Density 0.080%

    No Known Activations