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. 15014
    Prev
    Next
    INDEX
    Explanations

    countries and features related to mobile apps

    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
    184
    +0.39
    1.5%
    764
    +0.30
    1.2%
    1108
    +0.24
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.39
    0.01
    184
    +0.30
    0.00
    227
    +0.24
    0.01
    Negative Logits
     milano
    -1.05
     alberto
    -1.02
     fup
    -1.00
     fta
    -0.99
     guatemala
    -0.98
     roberto
    -0.98
     frankfurt
    -0.98
     sergio
    -0.98
     toledo
    -0.97
     santiago
    -0.97
    POSITIVE LOGITS
    bewerken
    0.56
     istore
    0.48
    MotionEvent
    0.48
    RunWith
    0.46
    енча
    0.46
    Compartir
    0.45
     MotionEvent
    0.45
    parsedMessage
    0.45
     아이콘
    0.44
    .
    0.43
    Activations Density 0.005%

    No Known Activations