© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 494
    Prev
    Next
    INDEX
    Explanations

    references to a specific location named "The Grove"

    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
    331
    +0.10
    0.3%
    390
    +0.09
    0.3%
    597
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.03
    1120
    +0.09
    0.03
    283
    +0.09
    0.01
    Negative Logits
     саны
    -0.62
                            
    -0.59
    Royce
    -0.58
    יא
    -0.57
    dc
    -0.56
    RunWith
    -0.54
    dial
    -0.54
    ngilizce
    -0.54
    FirebaseAuth
    -0.54
    -0.54
    POSITIVE LOGITS
     increa
    1.68
     fta
    1.62
     Grove
    1.60
     maneu
    1.58
     affor
    1.50
     ftu
    1.49
     fortn
    1.46
     stockholm
    1.44
     pollut
    1.42
    Grove
    1.41
    Activations Density 0.227%

    No Known Activations