© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 486
    Prev
    Next
    INDEX
    Explanations

    phrases related to people's names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    492
    +0.11
    0.3%
    687
    +0.10
    0.3%
    1565
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.11
    0.04
    283
    +0.10
    0.01
    1120
    +0.08
    0.03
    Negative Logits
     disambiguazione
    -0.68
    rungsseite
    -0.68
     kram
    -0.66
    <bos>
    -0.66
     மற்ற
    -0.63
    ുറ
    -0.58
    homonymie
    -0.58
     TextInputType
    -0.57
     kies
    -0.57
    müller
    -0.57
    POSITIVE LOGITS
     Lem
    1.60
    Lem
    1.43
    ese
    1.40
     eiffel
    1.10
     LEM
    1.08
     cushi
    1.07
     hoody
    1.06
     lamborghini
    1.04
     tucson
    1.03
     redé
    1.01
    Activations Density 0.260%

    No Known Activations