© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 993
    Prev
    Next
    INDEX
    Explanations

    height measurements in meters

    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
    776
    +0.09
    0.2%
    1842
    +0.08
    0.2%
    1343
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.09
    0.05
    776
    +0.08
    0.06
    595
    +0.07
    0.04
    Negative Logits
    <bos>
    -0.72
    rungsseite
    -0.64
    abestanden
    -0.60
    xnn
    -0.57
     pira
    -0.56
     notor
    -0.56
     cala
    -0.56
    onViewCreated
    -0.55
    Controllo
    -0.55
     ecuador
    -0.55
    POSITIVE LOGITS
     deleteAll
    0.75
     jopa
    0.64
     newArr
    0.62
     akár
    0.61
    utebol
    0.58
     eventName
    0.57
    iyle
    0.57
     zelfs
    0.55
     selectAll
    0.54
     exceeding
    0.52
    Activations Density 0.443%

    No Known Activations