© 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. 6686
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to political figures or celebrities

    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
    +0.19
    0.7%
    1870
    +0.09
    0.4%
    513
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1705
    +0.19
    0.03
    65
    +0.09
    0.04
    814
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.85
    /**
    -0.68
     expel
    -0.66
     mustered
    -0.63
     endow
    -0.58
    <?
    -0.58
     reunite
    -0.58
     assimilate
    -0.58
     enshr
    -0.57
     hoisted
    -0.57
    POSITIVE LOGITS
     applau
    1.04
     pecuni
    0.99
     soggior
    0.96
     tramont
    0.96
     isuzu
    0.95
     thermomix
    0.94
     corrom
    0.93
     magis
    0.92
     quæ
    0.92
     monaster
    0.91
    Activations Density 0.606%

    No Known Activations