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. 3105
    Prev
    Next
    INDEX
    Explanations

    high altitudes and geographic features related to mountains

    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
    1385
    +0.16
    0.5%
    906
    +0.14
    0.4%
    1609
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.16
    0.03
    906
    +0.14
    -0.00
    1385
    +0.08
    0.04
    Negative Logits
     esternos
    -0.52
    Obrázky
    -0.48
     redire
    -0.48
     expor
    -0.47
    SharedDtor
    -0.47
     panik
    -0.45
    ContentAsync
    -0.45
     konserv
    -0.44
     Desen
    -0.43
    ReusableCell
    -0.43
    POSITIVE LOGITS
     heights
    0.97
     getHeight
    0.94
     height
    0.94
     altitude
    0.92
     altitudes
    0.89
     elevation
    0.88
     elevations
    0.80
    height
    0.78
    altitude
    0.77
    heights
    0.74
    Activations Density 0.382%

    No Known Activations