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. 15384
    Prev
    Next
    INDEX
    Explanations

    formal text discussing sizes or scales

    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
    +0.13
    0.5%
    1416
    +0.13
    0.5%
    1265
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.13
    0.05
    1416
    +0.13
    0.04
    662
    +0.12
    0.05
    Negative Logits
    toprule
    -0.60
    ENODEV
    -0.56
     aislada
    -0.54
    alamualaikum
    -0.52
    glColor
    -0.52
    Beskrivelse
    -0.51
    glTexCoord
    -0.49
    glMatrixMode
    -0.48
    allclose
    -0.47
    psfrag
    -0.47
    POSITIVE LOGITS
     small
    1.14
    small
    1.11
    Small
    1.08
     SMALL
    1.07
     Small
    1.05
    SMALL
    0.98
     smal
    0.87
    tiny
    0.76
     tiny
    0.75
     smaller
    0.73
    Activations Density 0.092%

    No Known Activations