© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7686
    Prev
    Next
    INDEX
    Explanations

    terms related to coding, algorithms, and spatial dimensions in plots

    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
    906
    +0.20
    0.6%
    876
    +0.17
    0.5%
    1385
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.20
    -0.01
    906
    +0.17
    -0.00
    59
    +0.11
    0.03
    Negative Logits
     Krzysz
    -0.64
     Condado
    -0.60
     Haci
    -0.60
     Siria
    -0.59
     republi
    -0.58
     Embaj
    -0.58
     akut
    -0.57
     konserv
    -0.57
     Lider
    -0.56
     Ży
    -0.56
    POSITIVE LOGITS
     coordinates
    0.71
     swarovski
    0.60
    <bos>
    0.59
     tricot
    0.59
     lpg
    0.58
     mondeo
    0.58
     coorden
    0.57
     position
    0.56
     andreas
    0.56
     jetta
    0.56
    Activations Density 0.299%

    No Known Activations