© 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. 14430
    Prev
    Next
    INDEX
    Explanations

    obstacles or challenges related to healthcare access

    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
    1604
    +0.10
    0.3%
    908
    +0.08
    0.2%
    990
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    809
    +0.10
    0.04
    1604
    +0.08
    0.03
    1328
    +0.07
    0.04
    Negative Logits
    quirrel
    -0.50
     primit
    -0.48
     huwa
    -0.47
     grecque
    -0.45
    auces
    -0.45
    ETHING
    -0.44
     EINVAL
    -0.44
     umbre
    -0.43
     Româ
    -0.43
    tellations
    -0.43
    POSITIVE LOGITS
     progress
    0.65
     attempts
    0.51
     spontaneity
    0.51
     Attempts
    0.50
     progression
    0.50
     accessing
    0.49
     effectiveness
    0.48
    progress
    0.48
     obtaining
    0.48
    attempts
    0.47
    Activations Density 0.351%

    No Known Activations