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. 15410
    Prev
    Next
    INDEX
    Explanations

    information about equipment or devices

    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
    1961
    +0.16
    0.7%
    1937
    +0.14
    0.6%
    1892
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1961
    +0.16
    0.02
    1515
    +0.14
    0.01
    1892
    +0.13
    0.01
    Negative Logits
    Namara
    -0.60
    Millan
    -0.53
     Emilie
    -0.53
    Allister
    -0.52
     Isabelle
    -0.49
     Rü
    -0.48
    Cormack
    -0.48
     Bobo
    -0.46
     Schöne
    -0.46
     Egon
    -0.46
    POSITIVE LOGITS
     gear
    1.38
     Gear
    1.31
    Gear
    1.28
    gear
    1.27
     GEAR
    1.19
     gears
    1.18
     Gears
    1.05
    GEAR
    1.03
    gears
    1.02
    Gears
    0.98
    Activations Density 0.075%

    No Known Activations