© 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. 6-RES-JB
    11. 279
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the breeding and care of puppies, particularly in a positive light

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.11
    0.4%
    1872
    +0.10
    0.4%
    513
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.11
    0.04
    1667
    +0.10
    0.03
    1416
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.04
    ⓧ
    -0.87
     AssemblyCompany
    -0.74
    Vegeu
    -0.68
     censiti
    -0.64
    Vanjske
    -0.60
    脚注の使い方
    -0.58
    ApiOperation
    -0.58
    TestTools
    -0.57
    Enllaços
    -0.56
    POSITIVE LOGITS
     stockholm
    1.33
     riviera
    1.32
     Khart
    1.27
     Middles
    1.25
     unlaw
    1.25
     impractica
    1.22
     sovere
    1.22
     exorbit
    1.22
     guarante
    1.18
     impra
    1.17
    Activations Density 0.314%

    No Known Activations