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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1772
    Prev
    Next
    INDEX
    Explanations

    references to specific types of trees, particularly "pine."

    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
    597
    +0.10
    0.3%
    1092
    +0.10
    0.3%
    67
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.04
    690
    +0.10
    0.04
    422
    +0.10
    0.03
    Negative Logits
     pale
    -0.67
    <bos>
    -0.65
    Adicionar
    -0.65
    synthesize
    -0.62
    Liên
    -0.59
     happened
    -0.59
    def
    -0.58
    Cancelar
    -0.58
     admit
    -0.58
     implement
    -0.58
    POSITIVE LOGITS
     pine
    1.72
     Pine
    1.57
     PINE
    1.54
    Pine
    1.53
     Mlle
    1.48
     sappi
    1.46
     Intere
    1.43
     milf
    1.40
     hcm
    1.40
     Juf
    1.35
    Activations Density 0.259%

    No Known Activations